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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 16:31 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 17:32 — 2026-11-09 17:32（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：2026-11-09 16:31最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 16:29（北京时间）
版本更新 · v2arXiv:2609.32499

Learning an Anchored Prompt Space for Continual Adaptation of Large Language Models

Rongguang Ye, Zhan Zhuang, Yichen Wu, Ming Tang, Kede Ma

原文摘要

Continually adapting large language models requires acquiring new knowledge while preserving previously learned capabilities. Although jointly adapting model parameters and task-specific soft prompts is promising, it has two key limitations: previously learned prompts may lose effectiveness as the model evolves, and relationships among prompts that could support cross-task transfer are not explicitly learned. We propose Learning an Anchored Prompt Space (LAPS), which preserves historical prompt effectiveness and learns relationships among task-specific soft prompts to facilitate positive transfer. Historical prompts are first aligned with the updated model through self-distillation. LAPS then constructs an anchored prompt space whose vertices correspond to learned task-specific soft prompts and whose intermediate geometry is shaped by learnable Bézier control prompts. Once this space is learned, LAPS identifies the best-performing prompt for each task on its validation set, allowing the selected prompt to draw on knowledge acquired from related tasks. Experiments on the TRACE benchmark across three Qwen3 model scales show that LAPS consistently outperforms existing distillation-based, prompt-based, and joint prompt-parameter adaptation methods, improving overall task performance while reducing forgetting.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2508.20866

AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset

Amine Lbath, Massih-Reza Amini, Aurelien Delaitre, Vadim Okun

原文摘要

The increasing complexity of software systems and the sophistication of cyber-attacks have underscored the need for reliable automated software vulnerability detection. Data-driven approaches using deep learning models show promise but critically depend on the availability of large, accurately labeled datasets. Yet existing datasets either suffer from noisy labels, limited vulnerability coverage, or fail to reflect vulnerabilities as they occur in real-world software. This also limits large-scale benchmarking of such solutions. Automated vulnerability injection provides a way to address these limitations, but existing techniques remain limited in coverage, contextual fidelity, or injection success. In this paper, we present AVIATOR, the first AI-agentic vulnerability injection framework. AVIATOR decomposes vulnerability injection into a coordinated workflow of specialized AI agents, tool-based analysis, and iterative self-correction, explicitly mirroring expert reasoning. It integrates RAG and lightweight LoRA-based fine-tuning to produce realistic, category-specific vulnerabilities without relying on handcrafted patterns. Across three benchmarks, AVIATOR achieves high injection fidelity (91-95%) surpassing existing injection techniques in both accuracy and vulnerability coverage. When used for data augmentation to train deep learning-based vulnerability detection (DLVD) models, AVIATOR provides the strongest downstream gains in vulnerability detection. Across models and base datasets, AVIATOR improves average F1 scores by +22% over no augmentation, +25% over VGX, holding the prior best injection success rate, and +3% over VulScribeR, the prior state-of-the-art LLM-based injection model, with +7% higher recall and no precision loss. Its augmented data exhibits the lowest distributional distortion and scales efficiently with <2% syntax rejection at 4.3x lower cost than VulScribeR.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37181

LitUbik: open-source software for human-led systematic reviews with traceable AI assistance

Adolphe J. Bequet, Sebastien Laurent, Baptiste Bouvier

原文摘要

LitUbik is an open-source, self-hosted tool for conducting systematic reviews, from the registered protocol to the PRISMA 2020 diagram. LitUbik covers calibrated search equations, automated searching, deduplication, blinded multi-reviewer screening, full-text retrieval, snowballing, appraisal, extraction and reporting, on one server or across disconnected instances. At each stage, optional AI assistance from commercial or local language models offers proposals that a named reviewer accepts or rejects. Every AI call is logged, so the AI-use disclosure is written from a record. A systematic review of 31 papers on review tools, conducted in LitUbik, compares it with existing tools and illustrates its use. LitUbik is distributed under AGPLv3.

cs.DL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37179

Irreducibility Testing of Sparse Polynomials over Integers is NP-hard and Probabilistic Polynomial Time

Yichuan Cao, Xiao-Shan Gao, Qiao-Long Huang, Jiawei Nie

原文摘要

In this paper, we prove that irreducibility testing for sparse polynomials in $\mathbb{Z}[X]$ is coNP-hard under deterministic polynomial-time many-one reductions. That is, there exists no polynomial-time irreducibility test algorithm unless $\mathrm P=\mathrm{NP}$. We also provide an upper bound for this problem by demonstrating that the same irreducibility testing problem lies in $\mathsf{PP}\subseteq\mathsf{PSPACE}$; in other words, it can be solved in probabilistic polynomial time and, moreover, within polynomial space. The fact that $\mathsf{SparseIrred}_{\mathbb{Z}}\in\mathsf{PP}$ relies on the quasi-Riemann hypothesis result of Cureton--Thorner and on the uniform effective prime-ideal bound by Frei--Sofos--Widmer just posted recently.

cs.CC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.30027

Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark

Christine Park, Valerie Chen, Tim Dettmers

原文摘要

Frontier language models are rarely used in clinical workflows because the realistic, longitudinal benchmarks needed to develop them are scarce. Real electronic health record (EHR) data cannot be openly shared due to privacy, ethics or data use issues and it does not contain verifiable ground truth since the chart records only reflect what clinicians documented. We introduce Synthetic Hospital, an open, fully synthetic, fact-grounded longitudinal EHR benchmark that resolves the open sharing and verifiable ground truth barriers. Built entirely from public medical-education material with no protected health information, it comprises 1,268 longitudinal patients and 5,602 encounters, where every diagnosis, finding, and temporal relation is grounded in standard ontologies (ICD-10-CM, SNOMED CT, LOINC) and with a complete provenance chain back to its source medical education material. Synthetic Hospital is served through a simulated hospital record system that mirrors real EHR infrastructure (standard interoperability APIs, role-based access and function-calling interface). In a blinded review, physicians distinguished its records from real patient charts at near-chance rates (53%). Across 10 frontier and open models, none approaches ceiling: the best model reconstructs a patient's longitudinal problem list with a severity-weighted F1 of 0.73, level with the mean of seven physicians on a matched subset but well below the best of them (0.89), and misses roughly half of clinically relevant findings when summarizing a chart. Overall, these results highlight that Synthetic Hospital is a difficult and realistic test of clinical AI performance.

cs.AI · cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37178

INTR++: INterpretable TRansformer with better Accuracy, Interpretability, and Adaptability

Dipanjyoti Paul, Arpita Chowdhury, Maneet Chatterjee, Daichi Kitaguchi, Tanya Berger-Wolf, Tetsuya Sakurai, Wei-Lun Chao

原文摘要

Interpretable Transformers often perform well in domain specific settings but lose effectiveness beyond that. Achieving ViT-like broad applicability requires models with consistent performance across domains. Recent works on Interpretable Transformers, INTR and Prompt-CAM, were developed keeping domain adaptability in mind. Prompt-CAM leverages learnable prompts to promote adaptability. However, these prompts are fixed in nature and therefore struggle to adapt to domains with substantial variation in input image characteristics, resulting in reduced interpretability. To address this limitation, we propose INTR++, which extends Prompt-CAM by incorporating a lightweight Prompt Adapter Module (PAM). PAM enables prompts to be adaptive by enriching them with domain-specific knowledge, thereby ensuring consistent interpretability across diverse domains including those with varying image characteristics such as medical imaging, micro-scopic imaging, and remote sensing imagery. INTR++ retains the standard architecture and end-to-end learning of Interpretable Transformer based models, while adding only a small number of additional parameters compared to Prompt-CAM. We demonstrate that INTR++ delivers consistent improvements in all aspects across domains like animals, plants, medical imaging, microscopic imaging, remote sensing imagery and object-centric data.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37175HF 社区推荐

MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model

Brian Ko, Han Wang, Hejia Geng, Li Erran Li, Sherry Yang

原文摘要

AI research agents can propose, execute, and improve programs that solve machine learning tasks. However, executing each candidate program requires training and evaluating ML models, limiting how many candidates an agent can explore at each step. We introduce MLE-World, a world model finetuned from Qwen3.5-4B that predicts a program's terminal output (error traces, training logs, and validation scores) from its code and data description without executing it, together with a confidence score estimating the prediction's correctness. Because a prediction costs one inference call rather than a training run, MLE-World makes test time scaling (TTS) affordable for these agents. We build five TTS policies, guided by MLE-World, that compare several candidates per step by their predicted outputs: Sequential revision, Best-of-N, Pairwise judging, Fusion, and a UCB style rule that also adds an exploration bonus from this confidence score. Since predictions can be wrong, we run a candidate for real only when its confidence score is low. On 17 MLE-bench Lite tasks, MLE-World matches the real terminal output on 77.9% of held out programs, versus 41.1% for much larger prompted models. MLE-World guided TTS achieves up to 22.1% higher observed mean performance than the agent without a world model, with less real execution. Project webpage: https://mle-world.github.io/.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16600

The Geometry of Learning: Read-Write Asymmetry Across Training

Valeria Ruscio, Keiran Thompson

原文摘要

Pretraining and alignment update the same transformer weights, and we ask in which directions each stage changes them. The residual stream gives every matrix a shared coordinate system, in which a weight change can be compared with the principal subspace of the activations the matrix reads and with the prediction subspace of the unembedding. In this frame, alignment updates to the query and key matrices are enriched in the principal input subspace, while its updates to the output matrices are close to random relative to the prediction subspace, and the same signature appears in late pretraining and under every objective we apply to one checkpoint, so it is a property of the training stage rather than of the objective. The gradient of a linear map is a sum of outer products $δ_t a_t^\top$, and the residual stream enters this product through the activation $a_t$ for matrices that read from it and through the upstream gradient $δ_t$ for matrices that write into it. Read gradients therefore inherit the spectrum of the activations, which is the same under every objective, while write gradients inherit the geometry of the upstream gradients, which point into the prediction subspace only early in pretraining, when the output matrices acquire their prediction geometry. The raw read gradient follows the activation spectrum, the optimiser attenuates the concentration it inherits, and cancellation between tokens sets the scale of the update but not its direction. A write direction derived from the unembedding still changes predictions after alignment, and adaptation restricted to any single group of matrices remains effective, so the signature describes where training places its updates, not which matrices can carry them.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37174

Deep Holes and Aperture: Sign Laws for the Empirical Correlation of Lattice-Sampled Random Wave Fields

Tianhao Guo, Hao Luo, Xianzhong Li, Yuzhi Yang

原文摘要

A Gaussian random wave field is sampled on a lattice within a bounded aperture. After displacement, re-indexing leaves a residual in the Voronoi cell. We study whether the empirical lag correlation has positive real part throughout the cell. For each realization in a single-output reciprocal link with noiseless over-the-air return, this is equivalent to the negative returned gradient being a descent direction for all residuals and differentiable losses with nonzero error signals. Return noise is treated exactly. For isotropic fields, ball-shaped apertures, unshifted lattice points, and dilations approaching the critical covering radius, every minimizer is a deep hole except with exponentially small probability. A Gaussian vector on the deep holes determines the limiting failure probability, with explicit covariance and lattice-independent limiting normalization. Square, hexagonal, simple cubic, and body-centered cubic lattices have two, three, four, and twelve sign classes. At fixed target failure probabilities below the critical limiting value, this covariance determines the exact leading aperture constant. When the margin and target failure probability vanish jointly, that constant is common to lattice shapes within each dimension. A cubic correction yields vanishing relative tail error in a moderate-deviation regime. A non-asymptotic two-sided aperture law has explicit constants. With a Rayleigh-faded specular path and positive diffuse margin, a failure floor occurs at every positive path power exactly when the cosine of its phase change is negative somewhere in the cell. The floor vanishes for all directions exactly when the covering radius is at most a quarter wavelength.

cs.IT · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37172

DomeGS: Perceptually Consistent Background Completion for Unbounded 3D Gaussian Splatting in Virtual Reality

Anastasiya Pechko, Agata Szymańska, Piotr Borycki, Joanna Szelewska, Michał Mnich, Sławomir Tadeja, Przemysław Spurek

原文摘要

The growing need for high-quality 3D content remains among the most prevalent challenges in virtual reality (VR). Recently, novel view synthesis techniques have enabled rapid content creation, with 3D Gaussian Splatting (3DGS) emerging as one of the most promising methods for generating high-fidelity 3D scenes. However, using 3DGS to reconstruct unbounded outdoor scenes can leave horizons incomplete due to missing data or a lack of distant geometric constraints. Such incompleteness can break immersion, compromising VR's core characteristic. A typical workaround in traditional VR systems is a textured cube (skybox) or sphere (skydome) surrounding the environment to create the illusion of a distant background. However, these approaches struggle to blend seamlessly with the reconstructed 3DGS geometry. To address these issues, we introduce the DomeGS framework, which incorporates the skydome concept not as a flat background shell, but as a part of the reconstructed Gaussian Splatting 3D scene. By integrating the horizon and sky into the 3DGS representation, our method provides a unified, scene-consistent environment bridging foregrounds and backgrounds for greater realism. Experimental evaluation with N=36 users demonstrates that DomeGS significantly increases spatial presence (p=0.042) and realism (p=0.042) compared to the skybox baseline.

cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37170

From 12 to 200 Demonstrations: How ACT, Diffusion Policy, SmolVLA and $π_{0.5}$ Scale on a Low-Cost Arm

Simon Cowling

原文摘要

We trained four widely used imitation-learning policies, ACT, Diffusion Policy, SmolVLA and $π_{0.5}$, on nested subsets of 12, 25, 50, 100 and 200 teleoperated demonstrations of one pick-and-place task with distractor objects, using one fixed training recipe per policy. Every trained model was then run on a physical SO-101 arm on a fixed set of object placements: 1,340 scored episodes in 126 blocks. ACT, trained from scratch, rose from 1 success in 40 episodes at 12 demonstrations to 37 in 40 at 100. $π_{0.5}$ with its action expert fine-tuned was the best policy when data was scarce (16 of 40 at 12 demonstrations, 28 of 40 at 25) and then stayed near 70%; from 100 demonstrations ACT was ahead, by a margin this study does not fully resolve. SmolVLA and Diffusion Policy peaked near 50%, and both were affected by a failure to start: SmolVLA's arm never started moving in 47% of episodes, and Diffusion Policy hardly ever started until an idle lead-in was trimmed from the demonstrations. For $π_{0.5}$ the fine-tuning recipe mattered more than the amount of data: low-rank adaptation succeeded in 4 of 110 episodes, against 130 of 200 for action-expert fine-tuning. From the joint and camera recordings we place every episode on a four-stage ladder (started, reached the ball, carried it, delivered it) and show that for ACT more data moves failures from reaching, to grasping, to none, while the failures $π_{0.5}$ retains are in grasping. We also measure how weak a ten-episode block is as a measurement (the same checkpoint tested twice differs by 2 successes in 10 on average), separate seed-to-seed variation from that noise, and audit the human scoring against the recordings. Training length was fixed within each recipe, so the amount of data and the number of times it was seen change together; we state which conclusions survive that confound and which do not.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37169

Rènyi-Regularized Flow-Based Variational Inference for Bayesian Calibration

Exaucè Luweh Adjim Ngarti, Élise Arnaud, Léo Nicoletti, Victor Trappler, Arthur Vidard

原文摘要

Variational inference with normalizing flows provides a flexible posterior approximation for Bayesian model calibration, but struggles when the posterior has several modes separated by regions of low probability mass. We study this behavior in a two-parameter twin experiment and regularize the variational objective. Under Gaussian observation errors and a Gaussian prior, the corresponding minimization objective is the expected Tikhonov calibration objective minus the differential entropy of the approximating distribution. However, the expected Tikhonov term favors concentration near one of the modes, while entropy maximization does not guarantee multimodality. We introduce a regularization term based on Rényi divergence that encourages the approximate posterior to cover the prior support. In the connected bimodal case, a flow approximation represents both modes; in the case with well-separated modes, the flow and Gaussian mixture frequently miss one mode. The introduced regularization reduces the near-collapse fraction from 50% to 25%. While the regularization improves mode coverage in this experiment, it changes the Bayesian variational objective, introduces a trade-off in approximation accuracy, and does not provide a general solution to mode collapse.

cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34717

VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware

Borui Xu, Hongshi Tan, Wenqi Jiang, Bingsheng He, Ming Wu, Jason Zeng, Michael Heinrich

原文摘要

Vision-language-action (VLA) models increasingly run on edge devices aboard robots, where inference latency constrains closed-loop robot control. However, it remains unclear how to design VLA models, their inference software and edge hardware so that robots can run VLA inference in real time. Most VLA models report only task success, while prior studies cover limited action-generation strategies, divide inference into at most three stages, and lack comparisons of inference optimizations on the same models. Therefore, we introduce VLA-HWBench, a benchmark that measures 18 open VLA models on NVIDIA Jetson AGX Thor and AMD Ryzen AI Max+ PRO 395, with a seven-stage inference breakdown. Our study reveals three insights. First, action-generation strategy matters more than model size. It dominates 14 of 19 Jetson configurations, latency varies by $82\times$ on Jetson and $157\times$ on AMD, and parameter count explains at most 15% of latency variance. Models that generate long action chunks in a few flow-matching steps keep up with control, whereas token-by-token decoding does not. Second, kernel fusion with 4-bit weights helps most, running $π_{0.5}$ and GR00T N1.7 2.6-2.9$\times$ faster than PyTorch with torch.compile, but it exists for only these two models and only on the Jetson. Optimization also moves the time to the stages it shortens least, as CPU preprocessing grows from 12% to 39% of the GR00T N1.7 call. Third, after optimization, memory bandwidth limits only the stages that process few tokens on the Jetson, such as the denoising steps, whereas software limits all other stages, from unfused kernels to serial preprocessing on the host CPU. Overall, low-latency edge VLAs should use few action-generation iterations, inference software should extend kernel fusion and low-bit weights to more models and platforms, and edge hardware needs high memory bandwidth and a fast host CPU.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37166

LiveSearch: Questions as Executable Verifier Code for a Live Benchmark of Professional-Source Financial Search Agents

Sinuo Wang, Wentao Zhao, Jiacheng Lu, Rui Sun, Beidi Luan, Qiming Shi, Jing Li, Daxin Jiang 等 9 位作者

原文摘要

In finance, the answer that matters is usually the current one: prices, rates, and disclosures hold only as of a given day, so retrieving up-to-date facts is a core capability of a financial agent. Yet most financial benchmarks overlook timeliness. They fix each answer at annotation time, so the gold goes stale as markets move and, once leaked into training data, rewards recall rather than search and analysis. We introduce LiveSearch, a live benchmark that stores each question as executable verifier code: a typed program of calls to a professional financial data service, followed by a declarative extractor. The question is frozen, while its gold answer is determined by executing the program against professional financial data at evaluation time, and a daily job re-executes it with no human or language model in the loop. A memorized answer is thus likely outdated, and a model must reach the current one through tools and analysis. Construction is equally automatic: a language model only verbalizes programs enumerated from real tool responses and never chooses an answer. Under general web search, six contemporary tool-calling models reach 70.9% to 76.7% answer accuracy. Over three consecutive days, 70% of served questions change their gold value, and even under tolerance-aware matching, a literally reused earlier snapshot fails on a majority of questions within a single day. Per-question tracking uncovers dynamic shifts in correctness masked by aggregate accuracy.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37162

Coverage Under Contradiction: A Benchmark for Negation-Aware Retrieval

Pasha Abrishamchian, Eugene Yang, Andrew Yates, Nazli Goharian, Ophir Frieder

原文摘要

Coverage-evaluation benchmarks quantify whether retrieved evidence covers the different pieces of information needed to satisfy an information need. Existing benchmarks mostly consider factual claims that may already be known to pretrained retrieval components, leaving open whether retrievers find corpus evidence when it contradicts those priors. We study how retrievers behave when their parametric knowledge and the information in a corpus disagree. To do so, we develop a process to augment a nugget-based coverage benchmark with controlled contradictions. For each nugget, we create a negated counterpart and edit its supporting documents to support that negation while preserving the context. Applying this process to CoverageBench, a benchmark measuring information coverage, we create CoverageBench-Negate, spanning six datasets and roughly 63,000 original-edited evidence pairs (one per nugget-document link). We attach rich construction metadata to every pair and additionally provide out-of-family LLM judgments over all pairs and a human audit of a sample. In baseline experiments, BM25 separates original from edited near-twin evidence substantially better than dense retrievers (Qwen3 and Jina), which stay near chance. We release the benchmark on Hugging Face Datasets (nuggets, documents, pairs) together with the construction materials, including the prompts used to create it.

cs.IR · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37159

Physics-Guided Flow Matching: A Generative AI Framework for Global Total Electron Content Forecasting

Si-Tong Yang, Feng Ye, Xian Lu, Dong Lin, Benjamin C. Martinez

原文摘要

Accurate forecasting of global total electron content (TEC) is important for space weather monitoring and the reliable operation of satellite communication and navigation systems. We propose a physics-guided generative artificial intelligence (AI) framework for day-ahead global TEC forecasting. The framework builds on flow matching, which learns to gradually transform samples from an initial distribution into new samples that share the statistical characteristics of the target data. The proposed model incorporates ionospheric dynamics described by a partial differential equation (PDE) into this transformation process, guiding the changes between initial and target samples using physical knowledge. The model further combines the physical dynamics with statistical patterns captured from data to learn this transformation, adaptively adjusting their relative contributions at each location. The model is trained and evaluated using one year of global TEC data generated by the Thermosphere Ionosphere Electrodynamics General Circulation Model (TIEGCM). The results demonstrate that our model improves both spatial and temporal forecasting accuracy over representative benchmarks, including statistical, deep learning, and generative AI methods at all lead times and across latitudes. The average root mean square error (RMSE) is 39.2% lower than that of ConvLSTM and 23.8% lower than that of the same framework without physical guidance. The learned contribution weights vary systematically with latitude and across geographic locations, showing how the physical contribution changes across the forecast domain. These findings demonstrate that explicit physical guidance improves generative forecasts of global TEC and highlight the value of incorporating physical dynamics into generative AI modeling.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37732

ThinkJev: One Thought, Every Budget for Calibrated Typed Decisions

Xiaolu Ding, Kai Yang, Dongdong Liu

原文摘要

Many uses of language models end in a typed decision: a choice among a closed set of options, whose probabilities code can act on. Reading those probabilities from one forward pass is fast but often wrong on decisions that take several steps, such as arithmetic, counting, and date comparison. Letting the model think first fixes most of these errors, but costs seconds per decision instead of milliseconds. To pay for thinking only where it helps, ThinkJev builds a fast and a slow system from one open hybrid-thinking model that can answer directly or after a thought. System 1 reads the model's probabilities for the option letters when it answers directly; System 2 reads the same letters after the model has thought on the same cached prompt, so escalating repeats no work and both systems give probabilities over the same options. Because the letters can be read after any number of thought tokens, one sampled thought also gives the answer under every thinking budget. Without training, ThinkJev lets System 1 answer alone only where a statistical test on labeled dev data guarantees that its accepted answers stay under a target error rate. At a 5% target, Qwen3.5-27B answers 24.5% of 8359 test decisions this way with a realized error of 3.9% (Qwen3.5-4B and 9B: 6.5% and 0.0%). For the rest, stopping each thought as soon as its answer is confident reaches 81.6% accuracy, against 82.7% for always thinking, with 72% of the thought tokens. Choosing when to think from System 1's confidence alone saves less, because the decisions System 1 is least sure of are often not the ones thinking fixes. On the public items of JevBench, an independent benchmark of typed-decision services, Qwen3.5-27B thinks on 29.4% and is not distinguishable in accuracy from the two thinking APIs listed (exploratory). Code and data generators are available at https://github.com/ding-xiaolu/ThinkJev.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37157

What Survives Distillation? A Mechanistic Interpretability Study of GPT-2 and DistilGPT-2

Nabeelah Faumi, Deshan Sumanathilaka

原文摘要

Knowledge distillation compresses large language models into compact students that preserve aggregate metrics, yet the mechanistic consequences of depth-reduction distillation remain largely uncharacterized. This work applies linear CKA, logit lens analysis, attention pattern decomposition, sparse autoencoder feature statistics, and activation patching to compare GPT-2 and its six-layer student DistilGPT-2 across two canonical circuits: the Indirect Object Identification (IOI) circuit and the Greater-Than (GT) circuit. The results reveal a compression-collapse dichotomy: the IOI circuit suffers complete mechanistic collapse (DistilGPT-2: 35.2% accuracy vs. 94.8%, zero name-mover preservation), while the GT circuit survives with 87.7% task performance recovery through active remapping of the teacher's layer-9 comparison head into student layer~4 (mean Pearson r = 0.945). These findings demonstrate that circuit compressibility governs mechanistic survival under distillation, and that aggregate metrics are insufficient diagnostics for circuit integrity.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37153

FastBEVFusion: Simple Multi-Modal Fusion for 3D Object Detection at 50 FPS

Tom Sanitz, Emre Gülsoylu, Simone Frintrop, Christian Wilms

原文摘要

Reliable real-time 3D object detection based on LiDAR and camera data is critical for safety in autonomous driving, where systems must accurately perceive their surroundings with minimal latency. Many state-of-the-art systems achieve high-quality detection results but fail to meet real-time constraints, limiting their practical use. To address this challenge, we propose FastBEVFusion, a simple, fast, and robust fusion system for 3D object detection. Based on modality-specific features, FastBEVFusion projects these features into semi-aligned modality-specific BEV spaces, without relying on a computationally intensive and potentially error-prone depth estimation. Given these BEV spaces, we propose a light-weight, soft, and dynamic fusion module based on cross-attention, which adapts dynamically to the scene context and enables feature fusion across the entire BEV spaces. Experiments on the complex nuScenes dataset show that FastBEVFusion outperforms state-of-the-art real-time systems, and achieves over 50 FPS without deployment libraries. Additionally, our system shows strong robustness to calibration errors, making FastBEVFusion a powerful 3D object detection system for real-world applications.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37731

Amortized Localized Posterior Inference for Model Calibration with Application to an Ocean Turbulence Closure

Exaucé Luweh Adjim Ngarti, Élise Arnaud, Léo Nicoletti, Victor Trappler, Arthur Vidard

原文摘要

Model discrepancy may prevent a single calibration parameter from reproducing a physical response across the context domain. In addition, uncertainties in observations and contexts affect calibration and must be accounted for and quantified. We construct a family of localized posteriors by weighting observation likelihoods according to their proximity to a target context. Gaussian localization weights incorporate context uncertainty through covariance inflation, with reflection at domain boundaries and an optional correction for uneven context sampling. A conditional normalizing flow approximates the family of posteriors through amortized variational inference. Integrating the localized posteriors under a prescribed context measure gives the marginalized parameter distribution. In a twin experiment with the Branin-Hoo model, we compare global and localized inference under uniform and skewed context distributions. Localization reduces the reported aggregate predictive errors relative to the global posterior. An application to the k-$ε$ turbulence closure in a single-column ocean model, with atmospheric surface forcing as context, shows that localized posterior calibration reduces temperature and zonal-velocity errors relative to deterministic and global-posterior calibration. Both twin experiments are constructed to admit local compensation.

cs.AI · cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.20188

Structure-Aware Variational Learning of a Class of Generalized Diffusions

Yubin Lu, Xiaofan Li, Chun Liu, Qi Tang, Yiwei Wang

原文摘要

Learning the underlying potential energy of stochastic gradient systems from partial and noisy observations is a fundamental problem arising in physics, chemistry, and data-driven modeling. Classical approaches often rely on direct regression of governing equations or velocity fields, which can be sensitive to noise and external perturbations and may fail when observations are incomplete. In this work, we propose a structure-aware, energy-based learning framework for inferring unknown potential functions in generalized diffusion processes, grounded in the energetic variational approach. Starting from the energy-dissipation law associated with the Fokker-Planck equation, we construct loss functions based on the De Giorgi dissipation functional, which consistently couple the free energy and the dissipation mechanism of the system. This formulation avoids explicit enforcement of the governing partial differential equation and preserves the underlying variational structure of the dynamics. Through numerical experiments in one, two, and three dimensions, we demonstrate that the proposed energy-based loss exhibits enhanced robustness with respect to observation time, noise level, and the diversity and amount of available training data. These results highlight the effectiveness of energy-dissipation principles as a reliable foundation for learning stochastic diffusion dynamics from data.

cs.LG · math.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37149

GCSR-OCC: Geometry Calibration and Semantic Routing for Open-Vocabulary Occupancy Prediction

Bohua Wang, Congyang Zhao, Tianxiong Lv, Chenxu Zhao, He Zheng, Hangqi Fan, Leigang Luo, Zhihao Liao 等 10 位作者

原文摘要

Open-vocabulary 3D occupancy prediction represents scene geometry and semantics in a unified voxel grid, enabling recognition beyond predefined categories. One approach reconstructs scenes with 3D Gaussians and converts them into voxel occupancy. However, Gaussian scale inflation and excessive overlap can distort voxel occupancy predictions, while semantic mixing can arise within Gaussians spanning multiple categories and during 3D--2D semantic feature alignment. We propose GCSR-OCC, which combines geometry calibration and multi-mode query-conditioned semantic routing for indoor occupancy prediction from a single RGB image. The Evidence-Conserving Gaussian-to-Occupancy operator (EC-G2O) uses kernel mass normalization, $p$-norm aggregation, and a learnable gain to suppress scale inflation and excessive local evidence accumulation while calibrating occupancy responses. Multi-mode Query-First Gaussian Semantic Routing (MM-QGSR) matches multiple semantic modes per Gaussian to text queries and aggregates query-specific evidence into voxels through a learnable text-conditioned router. Fine-grained subclass queries and smoothed semantic aggregation further refine voxel-level predictions. Without 3D semantic annotations, GCSR-OCC achieves state-of-the-art performance in open-vocabulary occupancy prediction on Occ-ScanNet, with 63.31% geometric IoU and 27.44% semantic mIoU. It also reduces geometric aggregation latency from 19.76 ms to 12.88 ms. Our code will be made publicly available.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37148

EEG-Based Decoding of Musical Mode and Melodic Direction Using Empirical Mode Decomposition

Sergio Guillén, Lorenzo J. Tardón, Ana M. Barbancho, Isabel Barbancho

原文摘要

Electroencephalography (EEG) has proven to be a powerful tool for decoding neural activity in real-life scenarios, including the perception and processing of emotions elicited by music. Among the various musical features that modulate these responses, musical mode and melodic direction (or contour) play a central role. This work proposes a novel EEG feature extraction framework based on Empirical Mode Decomposition (EMD) to decompose EEG signals recorded during active piano performance for the detection of these two musical features. Energy-based descriptors were computed from the first four Intrinsic Mode Functions (IMFs) obtained through EMD and used to train a Wide Neural Network classifier. The model performance was benchmarked against several standard classifiers commonly employed in EEG classification tasks. Two experimental scenarios were explored: intra-subject and intersubject. In the former case, the proposed framework achieved average accuracies of 84%, whereas in the inter-subject case, accuracies reached 81% on average using the first IMF, with AUC-ROC values of 0.9 on average in both cases. A frequency-domain analysis revealed a strong correspondence between the IMFs and conventional EEG sub-bands, except for certain specific frequency components that were not fully represented. Predominant activations were observed over the frontal, temporal, and parietooccipital regions, areas consistently associated with music processing. Furthermore, the proposed method demonstrated robustness to handedness, successfully classifying EEG data across participants regardless of their dominant hand. These findings highlight the potential of EMD-based feature extraction for identifying music-related neural patterns and contribute to advancing research in Music Information Retrieval (MIR), affective neuroscience, and the broader understanding of the neural encoding of musical structure.

cs.SD · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.04974

Efficient Generative Transformer Operators For Million-Point PDEs

Armand Kassaï Koupaï, Lise Le Boudec, Patrick Gallinari

原文摘要

We introduce ECHO, a transformer-operator framework for generating million-point PDE trajectories. While existing neural operators (NOs) have shown promise for solving partial differential equations, they remain limited in practice due to poor scalability on dense grids, error accumulation during dynamic unrolling, and task-specific design. ECHO addresses these challenges through three key innovations. (i) It employs a hierarchical convolutional encode-decode architecture that achieves a 100 $\times$ spatio-temporal compression while preserving fidelity on mesh points. (ii) It incorporates a training and adaptation strategy that enables high-resolution PDE solution generation from sparse input grids. (iii) It adopts a generative modeling paradigm that learns complete trajectory segments, mitigating long-horizon error drift. The training strategy decouples representation learning from downstream task supervision, allowing the model to tackle multiple tasks such as trajectory generation, forward and inverse problems, and interpolation. The generative model further supports both conditional and unconditional generation. We demonstrate state-of-the-art performance on million-point simulations across diverse PDE systems featuring complex geometries, high-frequency dynamics, and long-term horizons.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37147

MAPLE-Sec: Mobility-Aware Partitioned Language-Model Engine for Roaming IoT Security

Yuhang Qiu, Ziwei Li, Jinfeng Xu, Jialiang Xie, Fangmin Ren, Shirong Guo, Jing Yang, Sunil Prajapat 等 9 位作者

原文摘要

Mobile Internet-of-Things (IoT) endpoints such as connected vehicles, wearables, and drones continuously cross heterogeneous network domains, creating handover-driven attack surfaces that static, cloud-anchored detectors cannot follow. However, three obstacles block real-time detection on such roaming endpoints: detection state is lost at every inter-domain handover; transmitting raw telemetry to a fixed detector exhausts the uplink and the device battery; and full-depth language model inference cannot meet millisecond latency budgets on constrained hardware. To tackle these challenges, we propose MAPLE-Sec, a mobility-aware partitioning framework that splits a compact, security-tuned language model across a roaming device and its nearest edge node. First, a trajectory-conditioned partition scheduler recomputes the split point from predicted handover timing, residual battery, and uplink quality. Second, a token-budgeted early-exit mechanism emits a verdict at the shallowest layer that meets a confidence threshold. Finally, a learned activation-compression codec migrates the intermediate inference state across edge nodes during handover without retransmitting raw telemetry. We formalize the partition-and-migration decision as an on-device constrained optimization solved in sub-millisecond time. Extensive experiments across the CIC-IoT and Edge-IIoTset corpora under both IID and non-IID roaming conditions demonstrate that MAPLE-Sec sustains detection across mobility events, improving the converged F1-score by up to 9.3\% relative to Cloud-only and by 2.9 percentage points over the strongest edge-collaborative baseline (EdgeShard), while reducing end-to-end latency by up to 2.5$\times$. Ablation confirms that the activation-compression codec reduces migration energy by 2.4$\times$ versus the raw-activation migration variant.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37146

Variational Optimal Control for Diffusion Guidance

Ruoyu Wang, Xinyi Ye, Yunshuo Shi, Liangyu Yuan, Beier Zhu, Chi Zhang

原文摘要

We present a variational control framework that connects sampling-time guidance and reward-based model adaptation through a shared Jacobian pullback. Starting from terminal reward maximization with a path-space KL penalty, the Gibbs variational principle and Doob transform yield a correction to the generative dynamics. A local denoising approximation exposes the pullback that transports output preferences to the controlled variable. This construction gives Variational Optimal Guidance (VOG) in state space and extends to Distilled Variational Optimal Control (DVOC) by amortizing locally improved endpoints into model parameters. The resulting controls share a local variational rule: VOG acts through the denoising Jacobian, while DVOC realizes the parameter pullback by endpoint distillation. Under a linear MMSE model, VOG's exact correction lies in the data subspace. On ImageNet, VOG reduces DiT-XL/2 FID from 2.27 to 2.04 at 250 sampling steps and from 7.58 to 4.44 at 25 steps. After 20 updates on Z-Image-Turbo, DVOC improves HPSv3++ and four held-out evaluator scores over the untrained model, with the highest corresponding means among the trained methods compared. These results connect inference-time control and reward adaptation through a common geometric principle.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37145

Beyond Parameter Protection: Fisher-Shaped EWC for Replay-Free Continual Learning

Liying Wang, Simone Magistri, Joost van de Weijer

原文摘要

In replay-free continual learning, Elastic Weight Consolidation (EWC) uses Fisher information matrix (FIM) to protect acquired knowledge by penalizing changes to historically important parameters. However, a local importance estimate at the retained solution does not in general characterize sensitivity after finite parameter displacement. This motivates controlling Fisher sensitivity over a neighborhood of potential future updates. We propose Fisher-Shaped EWC (FS-EWC), which extends the role of FIM from parameter protection to solution formation for future retention. During task learning, FS-EWC minimizes the worst-case empirical FIM trace within a prescribed neighborhood, explicitly favoring solutions that are less sensitive to bounded future displacement. At task completion, trajectory-based model merging constructs the retained solution from multiple optimization states rather than a single terminal iterate, after which FIM is estimated for subsequent consolidation. Experiments across multiple benchmarks show that FS-EWC improves performance over EWC, while controlled studies indicate a more favorable stability--plasticity balance and greater tolerance to parameter drift. These results suggest that effective knowledge retention requires both forming solutions with future retention in mind and protecting acquired knowledge.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.35542

Hypergraph-Enhanced Evidence Selection for Long-Context Multimodal Document QA

Wenxin Zhao, Jiachuan Wang, Xinyi Zhu, Jiake Ge, Haoyang Li, Yongqi Zhang, Shuangyin Li, Lei Chen

原文摘要

Long-context multimodal document question answering (QA) has become an important yet challenging task for modern vision-language models (VLMs), as it requires reasoning over evidence dispersed across pages and modalities within limited input budgets. Current pipelines adopt retrieval-augmented generation (RAG) to select multimodal evidence for downstream VLMs. However, existing systems mainly rely on static selection rules over fixed-granularity retrieval units such as pages or blocks, resulting in information loss during retrieval and suboptimal performance in downstream reasoning. To alleviate these issues, we formulate the core task as budget-aware evidence selection over structured document evidence and propose HyperDoc, a document RAG framework that constructs compact yet sufficient evidence while preserving document relations. Specifically, HyperDoc constructs a document hypergraph to explicitly capture structural, logical, and cross-modal relationships among multimodal document elements. Over this structured evidence space, HyperDoc performs adaptive cost-aware hyperedge selection based on query intent and input budget. Extensive experiments on three representative benchmarks demonstrate that HyperDoc outperforms various types of state-of-the-art baselines.

cs.IR · cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37729

Pooled Testing under Congestion: Operational Scaling Laws for Pool-Size Selection

Ioannis Dimitriou, Johan van Leeuwaarden

原文摘要

Classical pooled-testing rules choose pool sizes to reduce the number of tests. In practice, however, samples arrive over time, pools take time to form, testing capacity is finite, and positive pools create bursts of follow-up work. These operational features can make the test-efficient pool size far from the delay-efficient one. We formulate pooled testing with stochastic arrivals and finite testing capacity as a queueing system, and derive exact performance representations and asymptotic scaling laws for fixed-batch Dorfman testing and a dynamic two-threshold policy. The analysis reveals three distinct design regimes. When test usage is the main concern, the classical Dorfman rule is recovered and the optimal pool size scales with the inverse square root of prevalence. When delay accumulated while the laboratory is busy testing another batch matters, positive pools create service-time variability that grows more rapidly with pool size than the mean retesting burden, and the optimal scale shifts to the inverse cube root of prevalence. When waiting to assemble a pool is itself costly, the optimal fixed pool size remains bounded even as prevalence becomes very small. Under severe capacity scarcity, congestion remains relevant at the classical Dorfman scale: the square-root law survives, but with a capacity-dependent constant. Dynamic pooling separates two operational decisions that fixed pool sizes conflate. A lower threshold determines when routine testing should begin, while an upper threshold limits pooling when backlog is high. The lower threshold follows the cube-root scale, whereas the upper threshold primarily acts as congestion control. The results show how prevalence, capacity, and delay jointly determine pooling decisions and explain why operationally optimal pools can be much smaller than those suggested by test-efficiency calculations alone.

cs.IT · math.OC · math.PR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2504.04626

Exact Unlearning of Finetuning Data via Model Merging at Scale

Kevin Kuo, Amrith Setlur, Kartik Srinivas, Aditi Raghunathan, Virginia Smith

原文摘要

Approximate unlearning has gained popularity as an approach to efficiently update an LLM so that it behaves (roughly) as if it was not trained on a subset of data to begin with. However, existing methods are brittle in practice and can easily be attacked to reveal supposedly unlearned information. To alleviate issues with approximate unlearning, we instead propose SIFT-Masks (SIgn-Fixed Tuning-Masks), an exact unlearning method based on model merging. SIFT-Masks addresses two key limitations of standard model merging: (1) merging a large number of tasks can severely harm utility; and (2) methods that boost utility by sharing extra information across tasks make exact unlearning prohibitively expensive. SIFT-Masks solves these issues by (1) applying local masks to recover task-specific performance; and (2) constraining finetuning to align with a global sign vector as a lightweight approach to determine masks independently before merging. Across four settings where we merge up to 500 models, SIFT-Masks improves accuracy by 5-80% over naive merging and uses up to 250x less compute for exact unlearning compared to other merging baselines.

cs.LG

查看论文
arXiv ↗PDF ↗