跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 22:53 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 23:40 — 2026-11-08 23:40（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 22:53最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

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

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 14,661 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 22:48（北京时间）
版本更新 · v4arXiv:2506.07886

EgoM2P: Egocentric Multimodal Multitask Pretraining

Gen Li, Yutong Chen, Yiqian Wu, Kaifeng Zhao, Marc Pollefeys, Siyu Tang

原文摘要

Understanding multimodal signals in egocentric vision, such as RGB video, depth, camera poses, and gaze, is essential for applications in augmented reality, robotics, and human-computer interaction, enabling systems to better interpret the camera wearer's actions, intentions, and surrounding environment. However, building large-scale egocentric multimodal and multitask models presents unique challenges. Egocentric data are inherently heterogeneous, with large variations in modality coverage across devices and settings. Generating pseudo-labels for missing modalities, such as gaze or head-mounted camera trajectories, is often infeasible, making standard supervised learning approaches difficult to scale. Furthermore, dynamic camera motion and the complex temporal and spatial structure of first-person video pose additional challenges for the direct application of existing multimodal foundation models. To address these challenges, we introduce a set of efficient temporal tokenizers and propose EgoM2P, a masked modeling framework that learns from temporally-aware multimodal tokens to train a large, general-purpose model for egocentric 4D understanding. This unified design supports multitasking across diverse egocentric perception and synthesis tasks, including gaze prediction, egocentric camera tracking, and monocular depth estimation from egocentric video, and also serves as a generative model for conditional egocentric video synthesis. Across these tasks, EgoM2P matches or outperforms specialist models while being an order of magnitude faster. We will fully open-source EgoM2P to support the community and advance egocentric vision research. Project page: https://egom2p.github.io/.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.00713

Observatorio Lazaro: A self-populating database of anglicism usage in the Spanish press

Elena Alvarez-Mellado

原文摘要

This paper describes Observatorio Lázaro, a language resource that monitors unassimilated lexical borrowings (predominantly English lexical borrowings or anglicisms) in the Spanish digital press. Since April 2020 the system has automatically processed the daily output of a collection of news outlets, detected borrowings with a neural sequence-labeling model, and made the results available through a public web interface and API. The result is a continuously updated diachronic database which, at the time of writing, records more than two million borrowings across 1.88 million articles and 993 million running tokens of text (2020-2026). The paper documents the resource: we describe the end-to-end pipeline (acquisition, detection, post-processing, storage and access), the data model and the terms of availability; we evaluate the resource through the detector's held-out performance (span-level F1=0.86 for the borrowing class), inter-annotator agreement on the training corpus (Cohen's kappa=0.91) and a manual precision audit of 1,000 spans from the deployed data; and we situate it with respect to Spanish borrowing lexicography, annotated borrowing corpora and neology-monitoring observatories. The data shows that unassimilated anglicisms are used in the Spanish press at a frequency of approximately two anglicisms per thousand tokens, and that this rate remains stable. Our statistical analysis over six years reveals that the anglicism vocabulary in Spanish behaves as an open and growing class, with 58.7% of its types attested only once (53.6% after correcting for detection precision), and that its density is highest in the fashion, technology and lifestyle sections and lowest in political and institutional news. The resource is intended to complement static borrowing dictionaries and one-off annotated corpora by providing a continuously updated record of borrowing in the Spanish press.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.12088

RA-ClipScore: Making Generative Model Evaluation More Interpretable

Yifan Lu, Taras Kucherenko, Hedvig Kjellström, Judith Bütepage

原文摘要

Generative models can produce images nearly indistinguishable from real data, yet rigorous and interpretable evaluation remains challenging. Conventional metrics such as FID provide only scalar scores with limited diagnostic insight. Widely adopted CLIP-based metrics enable semantic evaluation beyond simple training class labels, but inherit limitations from CLIP's training paradigm that restrict attribute-wise analysis. We propose RA-CLIPScore, a novel metric that mitigates these issues and extends CLIP-based evaluation to spatial distribution alignment, measuring whether generated objects adhere to the positional priors found in the training data. RA-CLIPScore introduces dual prompts to decouple competing attributes and leverages local patch tokens to capture fine-grained regional semantics. We evaluate image generative models on their ability to match both attribute and spatial distributions of the training data. Extensive experiments show that RA-CLIPScore provides more robust and interpretable evaluations than prior methods, particularly under distribution misalignment or partially irrelevant textual attributes. We further demonstrate how it reveals spatial biases in generative models. User evaluations confirm that Regional Single Attribute Divergence based on our RA-CLIPScore aligns more closely with human perception of visual diversity than existing semantic metrics.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.17973

Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue

Olivier Tieleman, Samuel J. Bell, Ziyi Zhu, Ting Su, Elizabeth Kroll, Thomas D. Hull, Caitlin A. Stamatis

原文摘要

Depression is a leading cause of disability worldwide, yet validated questionnaires such as the Patient Health Questionnaire-9 (PHQ-9) often go uncompleted, yielding sparse, biased data. Users of AI mental health applications often describe their mood, sleep and functioning unprompted, producing a continuous record of symptoms. Here, we predict PHQ-9 scores from these conversations alone. As in many clinical language tasks, labels are scarce and imbalanced. We address both by fine-tuning Qwen 3.5 27B with a regression head and augmenting 3,111 ground-truth labels with pseudo-labels from a frontier reasoning model and iteratively trained intermediate models, expanding to 5,524 users with more balanced scores. On 422 held-out users, the model achieved MAE $= 3.98$, Pearson $r = 0.67$, and AUC $= 0.88$ at the clinical threshold (PHQ-9 $\geq 10$); AUC was $> 0.80$ across severity thresholds from PHQ-9 $\geq 3$ to PHQ-9 $\geq 24$, demonstrating that the model captures depression severity across the full clinical spectrum. These results support passive depression monitoring without self-report.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06523

H^2MARL: Hierarchical Heterogeneous Multi-agent Reinforcement Learning for Humanoid Robot Control

Xuemin Hu, Kaixin Li, Qingqing Xia, Yuxin Wang, Wei Xie, Bo Tang, Long Chen

原文摘要

Coordinated whole-body control of humanoid robots remains challenging due to high-dimensional coupled dynamics and substantial physical heterogeneity across joint degrees of freedom (JDoFs). Existing multi-agent reinforcement learning methods either employ coarse agent partitions or directly apply generic heterogeneous-agent algorithms, while hierarchical controllers commonly optimize high-level planning and low-level execution independently, leading to uncoordinated motion. In this paper, we propose H^2MARL, a hierarchical heterogeneous multi-agent reinforcement learning framework with two key mechanisms. We first formulate humanoid whole-body control using a JDoF-level physical-heterogeneity-aware policy factorization, where each torque-actuated JDoF is conditioned on an explicit descriptor of its actuation, kinematic, and dynamic properties. Moreover, we develop a closed-loop policy-executor co-optimization mechanism that jointly adapts the high-level pose planner and the low-level joint executor using shared interaction trajectories, thereby reducing the distribution mismatch between planning and execution. Extensive experiments in MuJoCo and Isaac Gym demonstrate that H^2MARL consistently improves locomotion stability, gait coordination, and motion quality over homogeneous, coarse-grained, and independently optimized alternatives.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06522

From Admission to Retention: Predicting Durable Offspring in Quality-Diversity Search

Corrado Calamita, Matteo Mendicini, Luca Ferrari, Riccardo Bertamini

原文摘要

Automated failure discovery can be framed as a diversity problem: the objective is to expose distinct ways a system fails rather than a single critical adversarial case. Yet uniform parent sampling provides no way to allocate search effort toward individuals likely to produce durable archive contributions. We study this credit assignment problem in an unstructured Quality-Diversity (QD) archive, testing whether signals available before an individual has reproduced distinguish offspring that merely enter the archive from those still retained generations later. Across a planar-arm benchmark and two robotic-locomotion tasks, the same signals are often associated with entry and persistence in opposite directions. In particular, lineage depth is the clearest such signal, and its persistence discrimination grows with population capacity, which is associated with lower turnover. Biasing parent selection toward the signals with the strongest measured association to survival nevertheless does not improve search: moderate bias matches uniform sampling, and strong bias reduces QD-score.

cs.NE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06521

Deliberate Latent Reasoning for Sequential Recommendation

Haobo Zhang, Qiannan Zhu, Yutao Zhu, Zhicheng Dou

原文摘要

Sequential recommenders are widely applied in real-world scenarios to model user preferences and behavior patterns based on user interactions. Recent advances in sequential recommendation enhance transformer-based models with latent reasoning to refine user representations by autoregressively generating intermediate reasoning vectors. However, exploring the optimal reasoning depth for diverse user histories remains challenging: existing methods typically employ a fixed number of reasoning steps for all users. This ``one-size-fits-all'' strategy often leads to suboptimal representation learning due to over-thinking in simple histories or under-thinking in complex ones. To address this issue, we propose DESRec, a deliberate latent reasoning framework that performs personalized latent reasoning to learn more informative reasoning states and enhance user modeling for sequential recommendation. Specifically, it designs a reasoning step selection module that identifies the optimal reasoning step for each user sequence during the training phase. Through a self-distillation mechanism, it compresses this most informative state into the final reasoning step, which serves as the final user representation for item ranking during inference. Moreover, it introduces a progressive preference extraction mechanism for personalized reasoning, which dynamically segments a user's history into a variable number of periods and summarizes each into a latent milestone representing the user's preference for that period. It will be used as the input of the subsequent reasoning. The number of milestones varies with the users' history, enabling a personalized reasoning over users' evolving interests. Extensive experimental results on six public datasets and four backbone recommenders demonstrate the superiority of DESRec over eight baseline models.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.10819

Deep Sets and event-level maximum-likelihood estimation for fast pile-up jet rejection at the ATLAS High Level Trigger

Mohammed Aboelela

原文摘要

Multiple proton-proton interactions occur in the same bunch crossing at the LHC ("pile-up"), with the mean number of interactions per bunch crossing reaching up to about 60 in Run 3 and up to about 200 at the High-Luminosity LHC. As a direct consequence, hadronic activity within each bunch crossing increases, making it more difficult to identify collisions of interest pertaining to multijet final states. This work introduces DIPz, an uncertainty-aware Deep Sets-based machine-learning model that estimates each jet's origin along the beam axis as a Gaussian likelihood using the set of charged-particle tracks matched to the jet. Next, the DIPz predictions for each jet are combined into a likelihood-based event-level discriminant, which is optimised to select events compatible with a single collision producing a given jet multiplicity. This combined approach provides a robust and computationally efficient method for pile-up rejection in multijet final states, applicable to real-time event selections at the ATLAS High Level Trigger (HLT). Deployed online during Run 3 data taking, this approach reduces background rates by more than a factor of two, and decreases CPU consumption by approximately one third relative to the baseline data-taking configuration. It provides an early, flavour-agnostic pile-up jet rejection layer at the HLT preselection stage, introducing a previously unavailable handle for high-multiplicity jet signatures targeted by ATLAS.

hep-ex · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06519

IDSISA: Influence-Distilled Sharded Training for Efficient Machine Unlearning

Deeraj SK, Sadhana Devarajan, Tanmoy Hazra, Anupam Shukla

原文摘要

Machine unlearning removes the influence of specific training examples to comply with privacy regulations. Full retraining gives strong guarantees but is computationally prohibitive at scale; approximate methods are efficient but lack formal guarantees. SISA (Sharded, Isolated, Sliced, and Aggregated training) achieves certified deletion through data sharding and independent retraining, but random partitioning scatters forget requests across most shards, and isolated retraining degrades utility. We introduce IDSISA (Influence-Distilled SISA), which uses influence functions to concentrate forget-prone samples into few shards and distillation from unaffected shards to recover utility lost to isolation. The deletion guarantee inherited from SISA's retraining step remains exact and requires no probabilistic qualification; the distillation-based utility recovery is a separately quantified, empirically bounded approximation ($ε_{\text{cert}} \leq 0.015$ in expectation). We further formalize certification under sequences of repeated deletion requests, where cross-shard distillation can create dependencies between shards; we prove that a closure-based cascading retraining procedure restores the deletion guarantee to the full aggregated model under any deletion sequence. Experiments on ResNet-18/CIFAR-10, ResNet-18/CIFAR-100, BiLSTM/IMDB, TCN/IMDB, and a fully connected network on Fashion-MNIST show $14-91\%$ better selective forgetting, up to $50\%$ better utility retention in relative terms (with consistent percentage-point gains on the other architectures, where a relative baseline is undefined), and unlearning-time changes ranging from $-6.7\%$ to $+6.4\%$ depending on architecture, relative to SISA.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06518

EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

Mingzhe Zheng, Yue Wu, Jing Tan, Chang Zou, Dengyang Jiang, Zeyue Tian, Xuanhua He, Ryan Xu 等 22 位作者

原文摘要

Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression, often depends on subjective aesthetics and has no uniquely correct target. Existing approaches typically rely on fixed rewards for visual quality, motion quality, and text alignment that poorly capture emotional intent and can invite reward hacking, while RLHF is difficult to scale and subject to individual aesthetic differences that complicate the calibration of facial, body motion, and chromatic cues across narrative contexts. We introduce EmoReward, a new self-evolving training mechanism that distills evidence reliability from reward traces collected during an actual training run to adaptively guide multi-reward weight allocation in subsequent training by determining which emotional evidence to trust and how much to weight it. EmoReward first plans specific grounding cues from the emotional prompt to guide evaluation, then uses heterogeneous signal primitives to score the generated video during the act stage. Reflective Reward Gating calibrates their contributions through instance-level gates for phase, face confidence, conflict, and subtlety, then renormalizes weights over the active set to produce the sample's fused reward. RewardMemory then estimates each primitive's reliability from rollout scores and outcomes within each emotional regime in the finished training run, then fixes bounded multipliers that calibrate fusion weights in the next training run without updating reward models. Experiments on HunyuanVideo 1.5 show improvements across multiple RL algorithms and compare EmoReward with other agentic reward methods under SAGE-GRPO. Ablations and transfer experiments on SD 3.5 and FLUX further support adaptive reward calibration for visual generation.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06517

Dialect Matters: A Dialect-Aware Baseline for Igala-English Machine Translation

Etuh E., Eli. A. Jiya

原文摘要

The massive permeability of intelligent systems in every sphere of human activities have greatly enhanced clarity, ease of work, and increased general global understanding which has significantly awaken the use of intelligent systems by all users. Intelligent systems greatly rely on precise dataset/corpus for the correctness of their output. Despite efforts by researchers to address Low-resource language in the Natural Language Processing (NLP), Igala still has zero parallel corpora despite efforts by researchers. We present a dialect-aware baseline for Igala-English machine translation, among first open systems and first with dialectal variation analysis. Our dataset of 1137 sentences (899 training) is first with dialect tags: Idah 459 (40.4%), Ankpa 297 (26.1%), Ibaji 160 (14.1%), Other 187 (16.4%), Ogugu 32 (2.8%). Same English yields 20-60 Igala forms. Mixed-dialect training achieves balanced BLEU 11.66 versus Idah-only model which drops 4.7 BLEU on Ibaji (13.2 on Idah, 8.5 on Ibaji), proving dialect fairness requires mixing. Fine-tuned from Helsinki-NLP/opus-mt-en-mul (78M), epoch ablation shows convergence at 8 epochs and overfitting at 15. BLEU 11.66, chrF 46.69. Analysis shows 899 sentences on log-linear trend consistent with African low-resource literature. This work provides first dialectal impact analysis for Igala and establishes baseline for future work.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06514

An Interaction-Aware Decision Framework for FDIC-Assisted Distressed Bank Acquisitions: Empirical Evidence from the FDIC Failed-Bank Panel and the SVB-First Citizens Case

Yousef Nejatbakhsh, Malihe Aliasgari, Parsa Safaee, Sina Shokoohyar

原文摘要

Acquirers of failed banks weigh acquisition value, regulatory protection, risk, buyer strength, and execution difficulty jointly, because each signal's meaning depends on the others: high non-performing loans matter less when government loss sharing absorbs the losses. The proposed Spider Network Filtering Framework encodes such dependencies as four interpretable interaction rules among five dimensions, yielding graph-inspired features for a logistic model and a Pursue/Caution/Avoid decision rule. We evaluate it on 55 acquisitions assisted by the Federal Deposit Insurance Corporation in 2008-2024 by acquirers with a parent listed in the United States. Six financial inputs come from regulatory reports published before each failure; two deal terms, which the winning bidder knows when it bids but investors learn at the announcement, come from the regulator's press releases. The outcome, a positive three-day abnormal return around the announcement, records the market's initial reception, not realized success. Under grouped, nested cross-validation, the Spider-enhanced model reaches a mean area under the receiver operating characteristic curve of 0.594, against 0.615 for logistic regression on the same inputs and 0.632 for ridge regression; permutation tests that repeat the full model selection give at most weak evidence that any of them ranks better than chance. The Spider score used directly does not rank better than chance, and an apparent link between target distress and higher returns disappears against a bank-sector benchmark. Thresholds tuned for the F1 score approve most acquisitions with negative returns and realize negative utility when each costs three times what a positively received acquisition gains.

cs.LG · stat.AP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06979

Uncertainty calibration in Bayesian M/EEG source imaging

Ismail Huseynov, Mohammad Orabe, Srikantan Nagarajan, Stefan Haufe

原文摘要

M/EEG source imaging requires accurate localization and reliable uncertainty estimates, yet posterior credible regions are rarely assessed for empirical calibration. We present a simulation-based framework for uncertainty quantification and calibration of empirical Bayesian inverse methods with closed-form conditional Gaussian posterior summaries. We compare Bayesian minimum norm (BMN) with sLORETA depth weighting and sparse Bayesian learning (SBL) with sparse basis field expansions (S-FLEX). S-FLEX allows retained coefficients to contribute nonzero marginal posterior variance at locations where voxel-wise SBL yields degenerate variances. For BMN, we derive joint source- and noise-variance updates through evidence maximization. We test whether adaptive noise learning yields near-calibrated uncertainties. Both methods retain residual miscalibration, motivating post-hoc isotonic recalibration of credible-region levels using empirical coverage. Simulations assess fixed- and free-orientation models across signal-to-noise ratios (SNR), source sparsity levels, and subject-specific head models, using oracle, baseline-estimated, and adaptively learned noise. Before recalibration, SBL+S-FLEX yields lower Wasserstein localization error, smaller posterior uncertainty, and coverage closer to nominal credibility than BMN+sLORETA. Isotonic recalibration improves both methods, with larger gains for conservative BMN+sLORETA posteriors; transfer across mismatched SNR, sparsity, and head models remains condition dependent. Noise specifications yield broadly consistent reconstruction and uncertainty trends within each estimator. In real auditory MEG data, SBL+S-FLEX provides more focal localization and tighter uncertainties than BMN+sLORETA, suggesting greater statistical power for identifying bilateral auditory sources.

cs.LG · cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06977

BlockLock: Reproducible LLM Inference with Fixed Batch Geometry

Xiuyuan Qi, Pedro Reviriego, Javier Conde, Shanshan Liu

原文摘要

Reproducible LLM inference requires that a request produces the same output regardless of the other requests in the batch. Existing solutions pay for this in different ways: batch-invariant kernels constrain every operator, and isolating prefill with fixed-shape decode ({our CoRun-style baseline}) gives up shared prefill compute and pads decode. We present BlockLock, which keeps shared batched prefill and pins only the numerical path of the protected request: it fixes the geometry that the request sees, with {two modes: BlockLock-Rows uses fixed-width rows and retains batched decode of all requests; BlockLock-Pack uses terminal-anchored packing with an isolated dummy segment, then extracts the protected request's KV state for target-only decode. Under a stated per-deployment contract, both modes preserve the target's output bitwise when its companions change.} Across five {dense} models (Qwen3-8B/14B, Llama-3.1-8B-Instruct, and Gemma-3-4B/12B-IT) and three single-GPU deployments (NVIDIA A6000, A100, and H100), we evaluate our approach on both tinyBenchmarks and BFCL{; we also include initial tensor-parallel experiments on two NVIDIA A6000 GPUs. Both modes preserve target sequences and Top20-logit bits in the reported tests.} At equal delivered work, {BlockLock-Rows} reduces latency by 53.5--55.0\% and improves throughput by 115.2--122.2\% relative to vLLM Batch-Invariant; compared with batch-invariant kernels, it needs no custom kernel implementations and constrains only the protected requests.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06512

Nowcasting Future Performance for Population Pruning in Survival-of-the-Fittest Training

Rico Städeli, Léo Meynent, Boris Knyazev, Damian Borth

原文摘要

Training high-performing neural networks often involves evaluating populations of candidate models with varying hyperparameters, architectures, or random seeds. Training every candidate to completion is computationally expensive, yet stopping seemingly weaker runs early risks discarding models that would ultimately perform better, as learning curves can cross. To address this challenge, we investigate whether intermediate training checkpoints can predict future model accuracy and enable more informed pruning decisions. Our nowcasters predict test accuracy five epochs ahead or at the end of training. They are trained with accuracy and loss histories, weight statistics, and SANE representations as inputs. SANE is a transformer autoencoder that encodes a checkpoint as a sequence of latent tokens. We then use the nowcasters in Survival-of-the-Fittest (SOTF) training. SOTF repeatedly ranks runs during training by predicted accuracy and stops the lowest-ranked ones. Our results show that weight statistics work best for five-epoch forecasts, and SANE representations work best for final accuracy prediction. For evaluation, we compare SOTF with pruning the population by current accuracy. In homogeneous model zoos such as the CNN zoos, pruning by current accuracy already retains a final model only slightly worse than the best. Model zoos with a larger spread in performance, such as the ResNet-18 and ViT zoos, are more difficult to prune by current accuracy alone. In these zoos, SOTF with nowcasted final accuracy almost closes the gap to the best model.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06508

ElecLoad: Adaptive Electricity Load Forecasting Guided by Multiple Events

Huajian Zhang, Mingyue Cheng, Xingpeng Gao, Xiaoyu Tao, Zhiding Liu, Jiqian Yang, Zhi Li

原文摘要

Accurate electricity load forecasting provides critical decision support for energy procurement, generation scheduling, and supply-demand balancing, contributing to the economic efficiency and operational reliability of power systems. However, future electricity demand can be affected by the complex interplay of multiple events described in Web notices, weather alerts, and event schedules. Their effects vary over time and can reinforce or offset one another, making electricity load difficult to forecast accurately. While existing methods can incorporate context as additional input, how to use the effects of multiple events and their interactions to guide the load forecasting process itself remains to be explored. To address this gap, we propose ElecLoad, a context-aware agent for multi-event electricity load forecasting that adaptively organizes the forecasting process. Specifically, we train ElecLoad to combine historical load with context to analyze each event's relevance to the target load, the timing of its effects, and potential interactions among events. Guided by this analysis, ElecLoad adaptively chooses to forecast the entire forecast horizon directly or to partition it into segments according to changes in event effects. When the horizon is partitioned, sub-agents independently generate initial forecasts for each segment. The main agent then reviews these forecasts, and the sub-agents perform selective refinement guided by its feedback. Experiments on multiple electricity load datasets show that ElecLoad achieves state-of-the-art performance in most evaluation scenarios. Code is available at https://github.com/zhjai/ElecLoad.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2512.10485

From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection

Chaomeng Lu, Bert Lagaisse

原文摘要

Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored. Recent work suggests that graph neural network-based and transformer-based models, including large language models (LLMs), yield promising results when evaluated on curated benchmark datasets. These datasets are typically characterized by similar data distributions and may contain synthetic samples, heuristic labels, or labeling noise. In this study, we systematically evaluate four representative DL models---Devign, ReVeal, LineVul, and VulBERTa---across four representative datasets: Juliet, Devign, BigVul, and ICVul. Each model is trained independently on each dataset, and the graph-based and CodeBERT representations adopted by these models are analyzed using t-SNE and centroid distance to examine vulnerability-related patterns. To assess realistic applicability, we further evaluate trained ReVeal and LineVul models, along with four open-weight LLMs, on VentiVul, our newly constructed temporally separated out-of-distribution (OOD) dataset comprising 200 recent vulnerabilities from Linux and Chromium. Our experiments reveal that current representation methods struggle to distinguish vulnerable from non-vulnerable code and that trained models generalize poorly across datasets with differing distributions and characteristics. When evaluated on VentiVul, performance drops sharply, with most models failing to detect vulnerabilities reliably or distinguish vulnerable functions from their patched counterparts. These results expose a persistent gap between academic benchmarks and real-world deployment, emphasizing the value of our deployment-oriented evaluation framework and the need for more robust code representations, higher-quality datasets, and evaluation methods that account for vulnerability-fixing changes.

cs.CR · cs.LG · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06504

NaijaFacts: A Framework for Disentangling Language from Knowledge in Facts about Nigeria

Zainab Afolabi, Nikita Kozodoi, Jack Butler, Babs Khalidson

原文摘要

Multilingual benchmarks for African languages mostly translate generic questions into local languages, measuring linguistic competence but not whether models know facts about Africa. We introduce \naija, a benchmark of factual and statistical questions about Nigeria, authored by native speakers and grounded in authoritative official statistics, with every question available in English, Nigerian Pidgin, \yoruba, Igbo, and Hausa. Answering similar questions for the UK and US yields a country by language matrix that disentangles a language effect (the model knows the fact but degrades in a low-resource language) from a knowledge effect (the fact is absent in every language). Across eight frontier and Nigeria-adapted models, the knowledge effect dominates: English-query accuracy is 49--50\% for the US/UK but 20\% for Nigeria. The language effect is smaller and tracks web representation, degrading from English to \yoruba{} (9 points on Nigeria, up to 24 on US/UK questions). We find scale does not help: the strongest models reach 66--79\% on the UK and the US but none exceed 31\% on Nigerian statistics. Extending to all 54 African countries with our best performing frontier model shows the same profile continent-wide, 96\% on culture and 98\% on politics against 26\% on statistics, so the gap is not specific to Nigeria.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06976

On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer

Zhenyi Shen, Junru Lu, Wei Liu, Jiangnan Ye, Jiazheng Li, Di Yin, Xing Sun, Tameem Adel 等 11 位作者

原文摘要

Prefill-to-Autoregressive Cross-model Transfer (PACT), a form of latent communication between language models, combines a larger model's prompt representations with a smaller model's efficient generation, offering a promising way to balance capability and inference cost. However, existing systems provide limited support for independently evaluating large-small model collaboration, and improved task performance alone does not establish whether the receiver benefits from the sender's information. We introduce PLatour, an open-source PACT framework that connects frozen models through lightweight, zero-initialized linear bridges trained directly with task rewards and supports hybrid-attention architectures. PLatour significantly outperforms open-source baselines on generation tasks and surpasses Mostik's reported results on shared mathematics and coding benchmarks using a substantially smaller sender. However, controlled experiments show that the gains on some tasks can be reproduced by uninformative sender signals, self-communication, or receiver-only training. We find that trainable bridges can act as parameter-efficient adaptation mechanisms without exploiting useful sender information. We therefore propose PACT-Check to quantify how much of a trained PACT system's gain genuinely comes from communication. Finally, we discuss the opportunities and challenges of PACT systems. Code is available at https://github.com/zhenyi4/platour.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06501

CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation

Chenyang Le, Pei Zhang, Yuxiang Chen, Bing Han, Derek F. Wong, Baosong Yang, Yanmin Qian

原文摘要

Simultaneous Speech Translation (SimulST) requires balancing translation quality and latency. While Large Language Models (LLMs) excel in offline translation, current LLM-based SimulST systems predominantly rely on prefix-incremental generation. This paradigm suffers from redundant Key-Value cache recomputation and necessitates external Voice Activity Detection to process unbounded streams. To overcome these bottlenecks, we propose an end-to-end interleaved read-write framework built upon an omni-modal LLM. By interleaving speech chunks and text tokens, our architecture achieves full KV cache reuse, natively supporting segmentation-free, infinite-length inference. Furthermore, to learn optimal streaming policies without rigid offline alignments, we introduce a novel Actor-Critic self-enhancement pipeline. An RNN-T Actor dynamically samples read-write trajectories, while an LLM-based Critic evaluates these paths via intrinsic semantic and latency rewards, distilling the optimal policy back to the Actor. Extensive experiments on sentence-level (FLEURS, CoVoST2) and document-level (MuST-C, ACL 60/60) benchmarks demonstrate that our model establishes new state-of-the-art quality-latency Pareto frontiers, substantially outperforming existing cascaded and static-alignment baselines.

cs.CL · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06500

Tools Need Not Speak in Text: Latent Context Compression for Agents

Yuetong Liu, Zhehao Zhou, Yitong Zhang, Haorui Chen, Jia Li

原文摘要

Large language model (LLM) agents typically append raw tool outputs to their context. Over multi-step interactions, long and noisy observations incur substantial context overhead and dilute the agent's attention to task-relevant information. Existing token pruning and summarization methods remain constrained by discrete text representations, limiting the achievable compression ratios. In this work, we challenge the prevailing assumption that agents must consume tool observations as explicit text tokens. To this end, we propose Coca-Cola, a continuous latent context compression model for LLM agents. Coca-Cola compresses tool observations into latent tokens and embeds them into the input embedding space of the agent. We further introduce Action-Preserving Training, which aligns the agent's next-action distributions under full and compressed observations. This trains the compression model to learn action-sufficient latent tokens that retain decision-critical information. Experiments with web-search agents on four QA benchmarks and two model families show that Coca-Cola reduces the agent's token consumption by 70.01%-89.24% and end-to-end runtime by 24.45%-55.97%, while consistently improving task performance. These results suggest that Coca-Cola offers a promising approach for context compression in agents. Our code is available at https://github.com/THU-Agent/Coca-cola.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06498

Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation

Georgios Feretzakis, Alexandros Papaspyridis

原文摘要

Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors. A signature proves who published a pack, not that its vectors encode its text. We study this text-vector integrity gap. A verifier that recomputes vectors and accepts them within a cosine tolerance concedes a predictable share of queries to an attacker who controls the vectors: the hijack rate equals the distribution of angular retrieval margins at the tolerance (the margin law). Margins are small in five corpora and two embedding models, so an idealised tolerance at the level of floating-point noise leaves up to 5.5% of queries exposed (at most 1.2% in any corpus once exact duplicate documents are excluded), and a threshold calibrated from our CPU INT8-FP32 comparison of a small embedding model (at the empirical 0.1% quantile of honest cosines) leaves 98-100% exposed; on a Raspberry Pi 5 running a local language model, such an attack lowers correct answers from 0.75 to 0.39. Integrity audits of compressed vector stores fare no better: on a FAISS product-quantisation index over 57,638 documents, tampered vectors that all pass the audit put the attacker's document first for 25% of targets. Verifying quantisation codes instead, with ambiguity decided by the verifier, a calibrated guard band and canonicalisation, accepted every honest vector in our samples on three platforms and left the publisher no choice. We also show that common floating-point and dynamic-INT8 inference pipelines are not bit-reproducible across batch sizes or architectures, and report pre-registered negative results on abstention, context pruning and semantic screening. We release code and data.

cs.CR · cs.IR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.30202

A Dual-Path Architecture for Scaling Compute and Capacity in LLMs

Markus Frey, Behzad Shomali, Joachim Koehler, Mehdi Ali

原文摘要

Looped transformers apply a shared block multiple times and have emerged as a parameter-efficient route to scaling compute in language models. However, at fixed FLOPs a looped model has strictly less capacity than a baseline transformer. We argue that compute, the number of sequential operations applied to a hidden state, and capacity, the parameters available at a single step, are distinct scaling axes that standard transformer layers conflate. We propose a dual-path block that exposes both axes as parallel pathways within a single layer: a deep sublayer re-applied $K$ times with shared parameters, and a wide sublayer with an enlarged feed-forward network applied once, combined by independent per-token gates. At two FLOP budgets, the best dual-path configuration surpasses both iso-FLOP single-axis controls on aggregate language modelling, commonsense, and math metrics, while using 17-33% fewer parameters than the width-scaled baseline. The learned gates are directly interpretable and show systematic per-token allocation: function words and lexical content trend wide, while punctuation, symbols, and arithmetic tokens trend deep. Our results suggest that compute and capacity can be scaled separately, with the model balancing the two token by token.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06496

LibriSpeech-Real-QA: A Benchmark for Streaming Question Answering

Zewen Zhan, Hui Lu, Xueyuan Chen, Huimeng Wang, Yikai Huang, Xixin Wu, Shiyin Kang, Bin Xia 等 9 位作者

原文摘要

Most speech large language models (SLMs) still process speech in an offline manner. They only start responding after they receive the complete speech segment. However, many real-world applications require streaming speech interaction, for which the audio continuously flows in and the machine is required to answer questions based on the so far received audio chunks. For example, a user may ask the system to continuously count how many times a person's name has been mentioned while they are speaking. We observe a lack of benchmarks and evaluation protocols for real-time speech interaction. Motivated by this, we propose LibriSpeech-Real-QA, a dataset and a benchmark for real-time speech interaction. We construct different types of real-time question-answer pairs from LibriSpeech to evaluate whether speech LLMs can identify target words in streaming audio. We evaluate several popular real-time commercial models and find that they still tend to respond only after the speech turn has finished. We demonstrate that we can enable a pretrained SLM to perform this task, where we explore several modeling designs and establish a solid baseline for future research.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06491

FPTR: Feasibility-Preserving Transactional Refinement for Deadline-Constrained Joint Beam and Resource Allocation

Minghao Kong, Zirong Liu, Jianhao Wu, Muyao Chen, Jianxin Wu, Rongjie Wang

原文摘要

Short-interval wireless schedulers must return a complete, feasible beam-and-resource allocation before each execution deadline, and a late or invalid output gives no utility in the current control cycle. Searching longer can increase transmitted traffic, but it may also miss the deadline or leave only an infeasible intermediate solution. We propose Feasibility-Preserving Transactional Refinement (FPTR), which always keeps a validated feasible allocation, the incumbent. Each refinement stage builds a separate candidate and leaves the incumbent unchanged. A candidate replaces the incumbent only if it is complete, passes the feasibility validator before its stage cutoff, and strictly improves the objective; otherwise it is discarded. Four refinement stages use this rule: buffer-aware resource selection, compatibility-group (CG) user sharing, beam-mask rebuilding from remaining demand, and joint reassignment of two resources. On 150 fixed synthetic instances, the full pipeline (Full) raises traffic by 3.83% on average over a lightweight beam-first reference and by 1.79% over its Base constructor. In a separate suite with matched inputs, Full exceeds six independent search baselines (ALNS, tabu search, GA, simulated annealing, iterated local search, and GRASP) by 6.68-8.35%, where outputs later than 100 ms receive zero utility. All 750 Full runs in the internal suite returned feasible allocations, and none exceeded 100 ms. Separating mandatory output construction from optional refinement lets spare computation time improve the allocation without endangering the incumbent. The open-source implementation supports independent reproduction.

cs.AI · cs.AR · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.22968

Certified Circuits: Stability Guarantees for Mechanistic Circuits

Alaa Anani, Tobias Lorenz, Bernt Schiele, Mario Fritz, Jonas Fischer

原文摘要

Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying circuits--minimal subnetworks responsible for specific behaviors. However, existing circuit discovery methods are brittle: circuits depend strongly on the chosen concept dataset and often fail to transfer out-of-distribution, raising doubts whether they capture the concept or merely dataset-specific artifacts. We introduce Certified Circuits, which provide provable stability guarantees for circuit discovery. Our framework wraps any black-box discovery algorithm with randomized data subsampling to certify that inclusion decisions over circuit components--neurons or edges of the model graph, depending on the base algorithm--are invariant to bounded edit-distance perturbations of the concept dataset. Unstable components are abstained from, yielding circuits that are more compact and more accurate. We validate across three architectures (ResNet, ViT, GPT-2) on vision (ImageNet and four OOD datasets) and language (IOI, IOI-Hard, Greater-Than) tasks. Certified circuits achieve up to 56% higher accuracy and up to 80% fewer components, and remain reliable where baselines degrade. Certified Circuits puts circuit discovery on formal ground by producing mechanistic explanations that are provably stable and better aligned with the target concept. Code: https://github.com/AlaaAnani/certified-circuits.

cs.AI · cs.CV · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06489

Risk-Sensitive Non-Parametric and Kernel Bandits

Devdan Dey, Sujoy Bhore, Avishek Ghosh

原文摘要

We study non-parametric bandits in which arms are evaluated using Cumulative Prospect Theory (CPT) rather than expected reward. We consider continuous action spaces with arm-dependent noise and propose Non-Parametric CPT Bandits ($\mathtt{NPCB}$), an optimistic algorithm that decouples mean estimation from CPT-based decision-making. We prove CPT regret of order $\widetilde{\mathcal O}\bigl(\sqrt{T\,\dim_E(\mathcal F,T^{-2})\,\log N(\mathcal F,T^{-2},\|\cdot\|_\infty)}\bigr)$, where $\dim_E$ is the Eluder dimension of the function class $\mathcal F$, $T$ is the time horizon, and $N$ is its covering number in the sup norm. This matches the order-wise regret of classical non-parametric bandits, showing that CPT risk sensitivity incurs no additional order-wise regret cost. We extend $\mathtt{NPCB}$ to unknown noise CDFs, retaining the known-CDF mean-learning term and adding a CDF-learning cost governed by a distributional Eluder dimension. We also study Kernel-CPT bandits and obtain information-gain-based regret bounds for a broad range of kernels, matching the corresponding risk-neutral kernel rates up to logarithmic factors.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06486

Model Merging Does Not Require Uniform LoRA Ranks

Zirong Xie, Zainab Afolabi, Nikita Kozodoi, Jack Butler

原文摘要

Model merging combines separately fine-tuned experts into a single model without retraining. Standard practice trains every expert at the same LoRA rank, which couples the rank choice across experts even though each domain has its own best rank. We show this coupling is a property of the merge method, not of merging. We train 36 experts on three domains (mathematics, instruction following, multilingual) at four ranks and three model scales, then merge with six methods at uniform ranks and at each domain's own best rank. Giving experts different ranks costs averaging and utility-based selection nothing, and gains them up to 1.8 pp of multi-domain accuracy, while the conflict-resolution methods are inconsistent and can lose up to 4 pp. The split has a simple cause. Merging keeps only a fixed share of the pooled spectral components, and methods that choose them by size discard many that would have reduced loss. They also tend to discard the same expert: the instruction adapter has the smallest singular values, so it is dropped almost entirely and IFEval falls by 16 to 25 pp. Choosing components by their effect on loss instead keeps all three experts, and leaves accuracy nearly flat across an 8$\times$ rank range (0.7 pp, against 6.7 pp for TIES at 4B scale). Rank can therefore be chosen per expert whenever the merge operator does not select by magnitude.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00180

Learning to Live: A Step Toward Lifelong Embodied Intelligence

Lirong Che, Peidong Wang, Yimeng Su, Jiong Wang, Yang Chen, Wenbo Fu, Zhenyu Huang, Tiancheng Xu 等 14 位作者

原文摘要

Embodied agents are usually organized around individual tasks, yet the physical world keeps changing between tasks and during execution. We introduce LIFE (Lifelong Intelligence from Experience), a framework in which a robot observes continuously, remembers selectively, and turns experience into new capabilities. RoboBeats, a family of lightweight streaming gates, tracks conditions set by the agent and discovers new events, deciding when an observation warrants a response or a memory write. Selected observations enter Plastic Memory, a flat store of images and structured records that keeps the source evidence, so new fields and indexes can be added when later questions need them. When existing tools fall short, Explore-Distill-Mount (EDM) turns solutions found during problem solving into validated, reusable tools and skills. Under matched protocols, RoboBeats substantially improves condition tracking over its base models and, at the same writing budget, retains more useful evidence for memory question answering than uniform sampling. A case study of limited scale, replaying 24 hours of continuous video recorded by a real robot, illustrates how the integrated system builds memory from a day of experience and uses it to answer everyday questions. LIFE takes a step toward robots that become more familiar with their surroundings and more capable through experience: learning not only to complete tasks, but to live in the world.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06484

Object-independent evaluation of small-data astronomical image classifiers: architecture, representation, and acquisition shortcuts

Eraldo Pereira Marinho

原文摘要

Reported performance in small astronomical image datasets can reflect object reuse, field-of-view differences, acquisition settings, and catalogue-derived properties as well as astronomical morphology. We designed \dataset{} to measure these effects in a four-class task comprising galaxies, globular clusters, nebulae, and open clusters. The dataset contains 370 catalogue-supported physical objects, each represented by three Digitised Sky Survey FITS bands, and uses a group-constrained split of 222 training, 75 validation, and 73 test objects. We compared a custom CNN--Transformer trained from scratch with ImageNet-pretrained ResNet-50 and ViT-B/16 under an adaptive full-field representation, a common angular field, and two central-region-masked controls, using three fixed seeds. In the one-pass object-independent test, mean balanced accuracy on the adaptive view was $0.773\pm0.014$, $0.874\pm0.054$, and $0.866\pm0.023$ for the custom model, ResNet-50, and ViT-B/16, respectively. No primary architecture contrast rejected its null after Holm correction; ResNet-50 and ViT-B/16 differed by 0.007 balanced-accuracy points (95\% cluster-bootstrap interval $[-0.048,0.062]$). Controls based on acquisition and catalogue metadata reached 0.721--0.735, and central-region-masked adaptive views reached 0.731--0.800. These results demonstrate generalisation to unseen physical objects, but also show that image context, acquisition settings, and catalogue-derived object properties carry substantial class information. In this regime, high accuracy cannot be interpreted as evidence that a classifier learned target morphology, and the comparison does not isolate architecture from pretraining.

astro-ph.IM · cs.CV

查看论文
arXiv ↗PDF ↗