跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 05:37 — 2026-11-19 05:37(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

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。

26,870 已收录论文22,374 AI 相关8,156 有修订112 HF 社区发现

浏览论文库

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

找到 22,374 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2611.20385

DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images

Emilio Ferrara

原文摘要

Can a vision-language model look at a picture of a chain reaction and tell what will happen? Recent multimodal models describe scenes fluently and solve textbook physics problems, which suggests they should also predict how a scene of ramps, ledges, pendulums, seesaws and dominoes plays out once a ball is pushed. We tested this claim on 30 models from 10 families and reached a clear conclusion: unaided, no model predicts the outcome reliably. We built DominoBench, a benchmark of still images of 2D rigid-body scenes whose outcome a physics simulator computes. It holds 854 items in 427 minimal pairs, in which a change of one to three grid steps in one quantity decides whether one person survives, and every item comes with a four-rung hint ladder ending in the exact calculation that decides the outcome. Unaided, frontier models from Anthropic, Google and OpenAI are right about the person whose fate flips in at most 75% of items and answer both twins of a pair correctly in at most 40%. Pointing at the deciding step helps little, and exact geometry given as text barely helps, yet once the deciding calculation and the quantities it needs, including speeds that a still image cannot show, are written out, the same models reach 80-92% on the deciding person, while small open-weight models stay near chance. Physical prediction from a still image therefore fails at the quantitative step: the strongest models use the deciding quantity when they are given it, but do not produce it on their own. For models that plan or act in the physical world, a fluent account of a scene is thus no evidence of a correct prediction: such models must find and compute the deciding quantity unprompted, and DominoBench tests whether they do.

cs.CV

新论文 · v1arXiv:2611.22338

Reliable Evaluation of AI Agents for Investment Research: A Framework for Performance and Validity Assessment

Dongnuan Tian, Yan Yu, Yangfan Liu, Wenjun Tang, Junting Kan, Xiang Wang, Sicong Liu, Yangyang Zhang 等 9 位作者

原文摘要

We consider the problem of evaluating AI agents undertaking investment-research tasks, where agents interact with external information sources and computational tools to produce financial analyses and research reports. An important challenge is that the quality of an agent's final output does not necessarily reflect the quality of its execution process, while the reliability of the resulting assessment also depends on the validity of the evaluation procedure. Furthermore, investment-research tasks differ considerably in their requirements for numerical accuracy, information retrieval, financial analysis and supporting evidence, making it difficult to assess agent performance using a uniform set of criteria. We propose a domain-oriented evaluation framework that distinguishes outcome quality from execution quality and accommodates these differences through task-specific criteria, deterministic validators and independent large language model judges. We also introduce an evaluation-validity mechanism that examines the integrity of evaluation inputs, reference information, supporting evidence and grading outputs, with expert review used to resolve identified deficiencies and significant grading disagreements. Numerical results show that the proposed framework can distinguish differences in agent performance across evaluation dimensions, while identifying potential reliability issues in the evaluation process. The associated implementation and evaluation materials will be made available on GitHub.

cs.AI

版本更新 · v3arXiv:2605.08777

Measuring and Decomposing Mode Separation via the Canonical Diffusion

Shaul Tolkowsky, Ori Meidler, Or Zuk

原文摘要

Mode separation, namely how sharply a distribution fragments into barrier-separated clusters, is a fundamental geometric property of densities, difficult to quantify in high dimensions. Modes are often the meaningful alternatives in the data, such as the conformations of a molecule or the distinct semantic types among a generative model's outputs. Mode separation is distinct from dispersion, which is what standard label-free tools capture: differential entropy rises with spread regardless of fragmentation, and PCA orders directions by variance regardless of barriers. Mutual information does capture it, but only given the latent component labels, which are usually unavailable. We measure mode separation through a single stochastic process intrinsic to the density, namely the unique reversible diffusion with $f$ as its stationary distribution and a constant scalar diffusion coefficient. From its autocovariance matrix we extract two readouts. The first, SSA (Sum of Squared Autocorrelations), is a scalar barrier-sensitive measure. The second, DA (Dominant Autocorrelation directions), gives linear projections ordered by metastability rather than variance. Under an isotropic-Gaussian null, we derive the limiting spectrum of the empirical autocovariance in closed form, generalizing the Marchenko--Pastur law. Its upper edge gives a noise floor that separates metastable directions from sampling noise. Both readouts use only samples and a score function, scaling to high dimensions through pretrained score-based generative models via Tweedie's identity. We apply our framework to three settings: (i) synthetic Gaussian mixtures, where SSA tracks mutual information; (ii) SDXL text-to-image generations, where SSA and DA capture structure that entropy and PCA miss; and (iii) molecular dynamics of alanine dipeptide, where DA recovers the known slow backbone dihedrals from static samples alone.

stat.ML · cs.LG · math.PR

新论文 · v1arXiv:2611.22335

Comparing Implicit and Explicit Language Attitudes toward the Dutch multiethnolect Straattaal in Humans and Large Language Models

Hedwig Oldenhof, Laura Rosseel, Anna Wegmann, Dong Nguyen

原文摘要

While language attitudes have been extensively studied in humans, the extent to which large language models (LLMs) encode similar associations between language varieties and social attributes remains unclear. Contemporary sociolinguistic research distinguishes between explicit attitudes, which stem from deliberative processing, and implicit attitudes, which arise from automatic processing. This study investigates whether LLMs exhibit human-like implicit and explicit language attitudes toward the Dutch multiethnolect Straattaal, particularly its association with migrant communities. We use closely matched designs to assess attitudes in humans and LLMs. For humans, we use an Implicit Association Test (IAT) and an explicit rating task. For LLMs, we use the LLM Word Association Test (LLM WAT) and the same explicit rating task. Human participants strongly associate Straattaal with individuals with a migration background at both implicit and explicit levels. In the LLM WAT, Straattaal is consistently associated with individuals with a migration background, with stronger associations observed in larger and newer models. When presented with the same explicit rating task as human participants, LLMs produce comparable response patterns. Overall, the findings suggest that many LLMs encode language attitudes resembling those observed in humans, however we also highlight important questions about how concepts and measures developed to study human attitudes should be interpreted in LLMs. This highlights the relevance of incorporating sociolinguistic perspectives and language variation into NLP research to better identify and mitigate socially and linguistically embedded biases.

cs.CL

新论文 · v1arXiv:2611.22334

BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning

Juyoung Park, Heejun Lee

原文摘要

Parameter-efficient fine-tuning of quantized large language models is dominated by QLoRA, which combines 4-bit weight quantization with FP16 low-rank adapters. We ask whether the FP16 adapter precision is necessary. Replacing it with a single binary bit per adapter parameter, combined with a learned per-layer scale $s$ and a Scaled Straight-Through Estimator, reduces adapter storage by 13-16x. We introduce two variants -- NormScale, which binarizes under a norm-preserving scale with a clipped STE, and LearnThresh, which makes the binarization threshold learnable -- unified under a framework we call BQ-LoRA. Our main theoretical contribution is a tight characterization of the BQ-LoRA hypothesis class: it has bounded entrywise norm, a typical-set spectral norm bound that is $Θ(r)$ times sharper than the worst case, a full-rank, near-isotropic update, and consequently a Rademacher complexity that yields an explicit $\tilde{O}(s_{\max}α\sqrt{d_{out}/(rn)})$ generalization bound. FP16 LoRA has no comparable a priori norm or isotropy control. On Qwen2.5 (1.5B-72B), BQ-LoRA exceeds QLoRA's benchmark averages at every scale by 0.8-3.5 points; on LLaMA-2 (7B/70B) it remains competitive at the same storage reduction but does not uniformly lead the strongest FP16-adapter baselines (LoftQ at 7B, QLoRA at 70B). On Qwen2.5-7B the binary adapter preserves the 4-bit base WikiText-2 PPL within 0.06 (9.86 vs. 9.80) while QLoRA worsens it by 0.59. The reduction applies to inference-time adapter storage and serving; training memory matches QLoRA and step time rises by under 4%. We translate the storage saving into a deployment study, BQ-SGMV, by extending Punica's SGMV kernel with a binary inner-product primitive: the same A100-80GB holds 15.6x more adapters in HBM, and our research prototype eliminates cache misses under a skewed synthetic workload.

cs.LG

版本更新 · v2arXiv:2611.15584

AI4Plasma II: Geometry-Aware Surrogate Modeling for Variable Electrode Gap GEC Plasmas

Hao Yang, Zhenyu Zou, Wenshuai Jie, Luowei Yin, Yufeng Wei, Daniel Zhengyu Huang, Chun Chen, Kangxin Liu 等 13 位作者

原文摘要

Industrial plasma process development requires broad exploration of operating and geometric parameters. Geometric parameters, particularly electrode spacing, affect discharge structure and processing uniformity. Exploring these parameter spaces through repeated high-fidelity simulations can be computationally expensive. Surrogate models can offer rapid predictions, but geometric variation complicates their application because the computational domain and discretization may change across samples. In this work, six geometry-aware surrogate models based on prescribed and learned geometry mappings, extended-domain representation, continuous coordinates, and geometry-native discretizations are compared in terms of their data requirements for accurate predictions of full plasma fields and ion density profiles near the wafer. The simulation dataset spans pressure, voltage, frequency, and electrode gap, with each reference case requiring an average simulation cost of 5.32 CPU h. To achieve a 2% mean error across the four plasma fields, prescribed-mapping Geo-FNO and Transolver require 100 training cases, compared with 250-1000 for the other models. Predicting ion density profiles near the wafer is more demanding and reveals larger differences among models, with prescribed-mapping Geo-FNO requiring the fewest training cases for the profile accuracy targets considered. To further reduce the data required for accurate predictions near the wafer, we introduce charge-separation weighting into the training loss, which reduces the prescribed-mapping Geo-FNO's minimum tested training requirement for a 5% profile error from 1000 to 100 cases. These results support prescribed-mapping Geo-FNO as a practical starting point for the variable-gap problem studied here when a suitable geometry mapping is available, while Transolver achieves the highest prediction accuracy with sufficient training data.

cs.LG · physics.plasm-ph

版本更新 · v2arXiv:2611.14775

DeNA-SGN: Deterministic Neighborhood Aggregation for Verified Spiking Graph Inference

Sanjay Das, Xi Zhang, Emily Herron, Prasanna Date

原文摘要

Graph learning on neuromorphic substrates requires an explicit spiking realization of neighborhood aggregation, supporting control and classification. We propose DeNA-SGN, which combines fixed OR and tie-inclusive Majority aggregation of binary node features with a learned signed-weight threshold classifier. A degree-dependent inhibitory construction implements Majority through shared control neurons, enabling a complete circuit compilation into SuperNeuroMAT. Across seven datasets and 41 mapped classifiers, native simulation matches the exported ANN on every evaluated class decision and output-spike pattern. On the new confirmatory Amazon Photo dataset, DeNA-SGN achieves 83.93+-0.93% current-readout accuracy and 71.61+-2.22% strict output-spike accuracy; Wiki-CS reaches 75.99+-0.54% over 20 public masks. In the matched Cora study, we achieve 74.90+-2.67% on current-readout and 68.57+-2.94% strict spike accuracy. Complete circuit and activity accounting supports analytical energy comparisons and identifies the cost of clocking inactive neurons in large deployments. Current argmax is decoded on the host, and energy is modeled rather than measured on hardware. These findings establish a reproducible route to useful graph classification with decision-matched spiking execution and explicit implementation costs.

cs.NE

新论文 · v1arXiv:2611.22331

DAP-MR: Degradation-Aware Prompt-Magnitude Routing for Real-World Ultrasound Super-Resolution

Ngoc-Hoang-Lam Le, Thi-An Le, Dinh-Hung Le, Manh-Hung Nguyen, Kai-Lung Hua, Ching-Chun Huang

原文摘要

When super-resolution models designed for natural images are used on ultrasound scans, relying on semantic text prompts can lead to unreliable results. The tags these models generate often do not match the actual restoration needs, and specialized medical terms may be misunderstood by general-purpose text encoders. Instead, prompts focused on common image degradations are more directly useful for guiding restoration. However, using a single prompt to describe both the type and severity of image degradation can entangle these factors, making it hard for the model to know how strong the degradation is. To address this limitation, we introduce Degradation-Aware Prompt--Magnitude Routing (DAP-MR). Each degradation type is represented by a dedicated token initialized from the contextualized EOS embedding of a degradation-oriented prompt and subsequently adapted during ultrasound SR training. A separate magnitude router predicts a continuous, input-dependent magnitude that modulates the corresponding token. Thus, language provides a degradation-aware initialization for what should be restored, while magnitude routing supplies an explicit signal for how strongly it should influence restoration. DAP-MR can be added to both one-step and multi-step diffusion super-resolution frameworks without changing their core structures. Our experiments--on synthetic datasets with both in-domain and under anatomical-domain shift, as well as unpaired real-world ultrasound data--show that DAP-MR delivers better restoration quality and generalizes more consistently across different domains.

cs.CV

新论文 · v1arXiv:2611.22330

Multistage Contextual Optimization for Vehicle Repositioning

Jinyu Zhang, Di Huang, Zhiyuan Liu, Nikolas Geroliminis

原文摘要

Ride-hailing platforms reposition idle vehicles to improve spatial supply-demand balances. This problem is prediction-driven and multistage: at each stage, the platform forecasts future demand, executes current decisions, and uses the resulting state to initialize the next stage. We formulate a multistage linear program (LP) with a macroscopic fundamental diagram (MFD) linking accumulation to trip completion. We then develop a multistage contextual optimization approach that uses decision performance to train the prediction model. The learning problem combines multiple coupled stages, context that depends on earlier decisions, and predictions that affect the objective, the constraint matrix, and the right-hand side of the LP. We derive the exact gradient, which has three parts: parameters change forecasts and hence decisions; earlier decisions change the current decision through the inherited state; and this state also changes forecasts as context. An equivalent adjoint uses reverse vector-Jacobian products, avoiding full solution and state-parameter Jacobians. Finally, forward propagation solves many stage LPs one after another, which makes training slow. We propose a parallel block evaluation algorithm that solves blocks of consecutive stages in parallel and repeatedly feeds each block output to the next block. We prove that the algorithm recovers the serial trajectory within a finite number of passes and that its gradient error remains bounded when it stops early. On New York City ride-hailing data, multistage contextual optimization yields 7.7% to 9.1% more business benefit than the same predictor trained by mean squared error, outperforms all compared baselines from five paradigms, and even outperforms realized demand fed to the same policy. With eight workers, parallel block evaluation shortens training by a factor of 1.86 without loss of decision performance.

cs.AI · cs.LG

版本更新 · v2arXiv:2608.05213

StyleComposer: Training-Free Multi-Reference Style Composition

Sanghyeok Lee, Jihye Kang, Namhyuk Ahn

原文摘要

The color, texture, and structure of an image can come from different references, but reference-guided generators transfer each reference as a single style signal. We find that in a diffusion transformer, every pathway that brings in a reference transfers multiple attributes, yet each attribute has one representation in which it is most directly controllable. Guided by this finding, we design StyleComposer to route color through the chromatic coordinates of the latent, texture through the attention keys and values, and structure through the queries, and to limit what else each route admits from its reference. Without training or inversion, StyleComposer follows the references and the prompt together more closely than stylization methods and multi-image generators, and it sets the strength of each attribute separately.

cs.CV

新论文 · v1arXiv:2611.22329

M$^3$-Test: Coverage Gaps in Joint-Perturbation Testing of Visual Question Answering

Enhui Wan, Xiaowan Wang

原文摘要

A visual question answering (VQA) model can pass every image-only and question-only test yet fail when the same changes occur together. Standard robustness reports average over conditions and therefore cannot say which accepted requests remain vulnerable. We introduce M3-Test, a coverage audit that aligns each clean input with its single-modality variants and a complete 5x5 family, 4x4 strength joint library, so that any reduced test suite can be replayed on the same requests. Across 2.6 million responses from four vision-language models, joint failures affect 26-29% of the Qwen questions that pass all 40 single-modality tests, although fewer than 0.6% of their joint records fail. Passing the 25 maximum-strength corners does not close this gap: 11-14% of the accepted questions still fail elsewhere in the library. Re-executing the archived failures reproduces about 90% of them, against a 0.3-0.6% flip rate among matched passing controls, and re-checking the most fragile failure records supports 80-89% of them. On the evidence examined, neither execution noise nor grading error can fully account for the gap. The same aligned grids make previous evaluations reusable. On held-out images, a risk order learned from other models discovers about 80% of affected Qwen questions within 25 additional queries, compared with 65-68% for maximum-first and 53-57% for pairwise covering arrays. M3-Test thus turns a passing robustness suite into a request-level account of what remains untested, supporting acceptance, regression review and test allocation.

cs.CV

新论文 · v1arXiv:2611.22328

PVTSizing 2.0: A Fast and Reliable Analog Circuit Sizing Operator for Agentic EDA Workflows

Zichen Kong, Minghuan Song, Xiyuan Tang, Ziming Wei, Yi Zhong, Yuan Wang

原文摘要

Analog circuit design automation requires both coordinated tool execution and efficient numerical search. Large language models (LLMs) offer new ways to organize tool execution, but finding one sizing that satisfies specifications across process, voltage, and temperature (PVT) corners remains costly. PVTSizing 2.0 addresses these needs through a human-agent workflow built around an independently usable numerical optimizer. An agent carries the designer's approved task through execution and result review. The optimizer reduces unnecessary training through loss-guided updates and uses critic-guided local refinement to explore additional candidates while accounting for cross-corner conflicts. An optional LLM adviser supplies parameter relationships to focus numerical search on circuit-informed directions, while the optimizer selects adjustment amplitudes and verifies their effects through simulation. Across four circuit benchmarks, the standalone optimizer completes all 40 runs and achieves a 7.3x speedup in overall mean runtime over the original PVTSizing, with a comparable mean sample count. In a separate study, the best tested knowledge-injection configuration further reduces mean runtime by 39.9% and simulation samples by 35.4% relative to the standalone optimizer.

cs.AR · cs.LG

新论文 · v1arXiv:2611.22323

Agent Trajectories as Evidence for Software Quality Assurance

Jonathan Ullrich, Julien Siebert, Michael Kläs, Adam Trendowicz, Andreas Jedlitschka

原文摘要

Autonomous software agents increasingly plan, implement, and test software with limited human oversight. Their decisions may introduce implicit assumptions that final code and passing tests do not adequately expose. We propose analyzing observable agent trajectories alongside software and agent specifications and AI generated artifacts as evidence for targeted quality assurance. The aim is to prioritize consequential decisions for scrutiny, investigate their possible contribution to software problems, and inform improvements to specifications and development practices. Industrial experience motivates the idea; available execution records and preliminary analysis methods make it plausible. However, trajectories alone do not establish that decisions are justified, outcomes acceptable, or corrective changes effective. We ask how this evidence can support review, diagnosis, and continuous quality improvement, and when simpler QA approaches suffice. Perspectives from requirements engineering, verification and validation, agent systems, causal inference, empirical software engineering, and human factors could help develop and evaluate the idea.

cs.SE · cs.AI

版本更新 · v3arXiv:2609.23466

RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents

Fanyu Zhao, Ruike Cao, Liang Dong, Fugen Yao, Jian Xu, Guanjun Jiang, Yifei Zhao, Yinsheng Li 等 9 位作者

原文摘要

Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at every query, making long-horizon performance increasingly dependent on retrieval quality and contextual reasoning as histories grow. Parametric memory encodes experience directly into model computation, but existing approaches provide limited support for cross-session memory evolution. Their coupling to a specific backbone further restricts memory reuse after model replacement. We introduce RPMem, a two-stage architecture that compiles each session into a model-independent latent memory through forward computation and selectively integrates it with retained memory via a task-trained recurrent gate. The consolidated memory is then mapped to backbone-specific low-rank adaptation (LoRA) parameters, allowing the encoding capability to transfer when the backbone is replaced. Evaluation across three long-term memory benchmarks and five diverse backbones demonstrates broad generalization with near-constant update cost and memory footprint. With Qwen3-8B on PERMA, RPMem reaches 85.52%, outperforming the strongest parametric and text-based baselines by 5.32 and 12.98 percentage points, respectively. Ablations validate the complementary roles of session compilation and cross-session consolidation, while dynamics analyses reveal that the gate acquires task-specific memory integration strategies. These results establish RPMem as a lifecycle-independent parametric memory framework that maintains evolving cross-session memory that remains reusable across backbone replacements. Our code is available at https://github.com/Quark-Medical/rpmem/tree/main.

cs.CL · cs.AI

版本更新 · v2arXiv:2507.14845

Training Self-Supervised Depth Completion Using Sparse Measurements and a Single Image

Rizhao Fan, Zhigen Li, Heping Li, Ning An

原文摘要

Depth completion is an important vision task, and many efforts have been made to enhance the quality of depth maps from sparse depth measurements. Despite significant advances, training these models to recover dense depth from sparse measurements remains a challenging problem. Supervised learning methods rely on dense depth labels to predict unobserved regions, while self-supervised approaches require image sequences to enforce geometric constraints and photometric consistency between frames. However, acquiring dense annotations is costly, and multi-frame dependencies limit the applicability of self-supervised methods in static or single-frame scenarios. To address these challenges, we propose a novel self-supervised depth completion paradigm that requires only sparse depth measurements and their corresponding image for training. Unlike existing methods, our approach eliminates the need for dense depth labels or additional images captured from neighboring viewpoints. By leveraging the characteristics of depth distribution, we design novel loss functions that effectively propagate depth information from observed points to unobserved regions. Additionally, we incorporate segmentation maps generated by vision foundation models to further enhance depth estimation. Extensive experiments demonstrate the effectiveness of our proposed method.

cs.CV

新论文 · v1arXiv:2611.22321

Beyond Episodic Recall: Experience-to-Knowledge Evolution for Lifelong Embodied Navigation

Weitao An, Chenghao Xu, Xu Yang, Cheng Deng

原文摘要

Lifelong embodied navigation requires agents to accumulate experience through continuous interaction and reuse it for subsequent goal searches. Existing memory-enhanced methods typically retain historical observations or construct structured scene representations. However, storing observations or high-dimensional semantic embeddings incurs growing storage costs. Meanwhile, structured representations support retrieval and semantic reasoning but do not explicitly evolve accumulated experience into environment-specific knowledge. To address these limitations, we propose Experience-Evolving Memory (EvoNav), a novel two-timescale memory framework. It organizes semantic observations, spatial relations, and task-feedback cues into sparse experience atoms. During online operation, experience atoms continually consolidate repeated observations and form dynamic links based on transitions. At the slower timescale, EvoNav distills accumulated category co-occurrences and feedback signals into environment-specific structural knowledge without relying on predefined object--room relations. For each new goal, EvoNav combines direct goal evidence from experience atoms with learned structural knowledge to guide goal-directed search on the current traversability map. Experiments on single-goal, sequential multi-floor, and multimodal navigation demonstrate effective experience reuse and improved path efficiency with compact persistent memory, together with successful transfer to a real robot.

cs.RO

版本更新 · v3arXiv:2608.12253

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

Simon Yu, Nicholas Tomlin, Marwa Abdulhai, Ximing Lu, Derek Chong, Abe Hou, Dilara Soylu, Sergey Levine 等 10 位作者

原文摘要

Multi-agent reinforcement learning (MARL) for human-AI interaction usually trains the agent against a single large language model (LLM) that simulates the user. We show that agents trained this way can systematically fail to generalize, and we trace the failure to simulator collapse: the simulator LLM is mode-collapsed, and a policy trained against it learns narrow strategies that exploit the simulator's mode behavior; these strategies transfer poorly to unseen simulators and to real users. We formalize the collapse and propose two solutions. Verbalized Sampling, applied at inference time, samples each simulator reply from a verbalized response distribution. Co-Training, applied during training similar to self-play, co-evolves the simulator as the policy, so the policy cannot exploit the mode behavior. A population variant samples the simulator for each rollout from a pool of recent checkpoints. We validate both solutions on three benchmarks: Persuasion for Good, tau^2-bench, and CooperBench. Verbalized Sampling improves held-out success by up to 9% over single-simulator RL, and Co-Training pushes gains further to 14%; the human study shows similar gain on real users. Both solutions also preserve the policy diversity that collapses under single-simulator RL. Overall, our findings on simulator collapse point to diverse simulators as a requirement for RL agents that serve real users. We release SCOPE, an open-source framework for Population Co-Training in multi-agent RL.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.22318

Breaking Visual Conventions: Spectrally Coupled Weight Perturbation for Creative Image Generation

Fu Feng, Ruoheng Zhou, Yucheng Xie, Xu Yang, Jing Wang, Xin Geng

原文摘要

Text-to-image (T2I) models often produce high-quality images that follow familiar visual conventions, even in response to open-ended prompts such as ``a creative [CLS]''. Existing methods encourage novelty by exploring semantic conditions or modifying features and guidance during denoising. Pretrained weights offer a complementary source of creative variation, but unstructured perturbations can have little visual effect or degrade image quality. We introduce Coupled Spectral Perturbation (CosPert), a training-free method that targets attention projections in layers identified by a one-time sensitivity analysis. For each projection, CosPert uses a shared random transformation and its transpose to couple updates to the singular-vector factors while perturbing the spectral gains. A common relative budget calibrates the magnitude of weight changes across projections, and a sigmoid schedule concentrates their influence in early denoising and gradually attenuates them during refinement. CosPert provides plug-and-play creativity enhancement at inference time. Once the perturbations are prepared, sampling requires no auxiliary networks or additional model evaluations. On both FLUX.1 and Stable Diffusion 3.5, CosPert enhances visual creativity, producing more varied object structures while preserving category identity. Across 50 object categories, CosPert achieves the highest mean CREward among the evaluated methods while maintaining strong prompt alignment.

cs.CV

新论文 · v1arXiv:2611.22317

SIDUMN: Self-Supervised Image Denoising Under Symmetric Multiplicative Noise

Nyan Htet Naing, Gyeongha Hwang

原文摘要

Self-supervised denoising is challenging when the corruption is multiplicative and signal-dependent. In this letter, we propose SIDUMN, a symmetric noisier framework for self-supervised denoising under mean-one symmetric multiplicative noise. Given noisy observations and the noise law, the method samples an independent synthetic noise factor from the same law and constructs two complementary noisier images by applying the factor and its reflection about one. The denoising network is trained to predict one noisier image from the other, and at inference the reconstructions of $K$ such antithetic pairs are averaged. We show that the population target of the training loss is the clean conditional mean minus a multiplicative cross-term. We further prove that, for any trained network, antithetic averaging never increases the expected squared error of a single noisier-input reconstruction. Numerical results validate the theoretical findings and the proposed method.

cs.CV

版本更新 · v2arXiv:2610.04081

AEGIS: Differentiable Mars Climate Model with Neural Closures

Sameera S Kashyap, Victor Cruz, Angel Yepez, Razvan Marinescu

原文摘要

General circulation models (GCMs) are the primary tool for simulating planetary atmospheres. They play a vital role in understanding Mars's atmosphere, as forecasting its unique weather is mission-critical for operations such as entry, descent, and landing. Mars poses unusual challenges for these models, as observations are sparse compared to Earth. In addition, a thin $CO_2$ atmosphere alongside a radiatively active dust cycle creates a volatile atmosphere with large diurnal temperature swings and no true terrestrial analog for validation. Existing Mars GCMs, including the LMD PCM, the NASA Ames Mars GCM, and PlanetWRF, are mature and physically detailed but are implemented in legacy Fortran with finite-difference or finite-volume solvers, and they do not expose gradients for calibration or machine learning. Here we present AEGIS, a modular differentiable Mars climate model that couples Mars's unique atmospheric physics to the Dinosaur dynamical core, with interfaces for neural closures. We showcase stable ten-Mars-year simulations that reproduce the seasonal $CO_2$ cycle while conserving the total $CO_2$ inventory, capture realistic large-scale surface-temperature structure, and produce surface pressure that follows Mars Orbiter Laser Altimeter (MOLA) topography. Gradients through coupled trajectories agree with finite differences and support physical calibration and neural training. We compare with conventional GCMs, highlighting the framework's computational efficiency and differentiability.

astro-ph.EP · astro-ph.IM · cs.AI

版本更新 · v2arXiv:2611.18770

AerialOcc: Unified 3D Aerial Perception without Task-Specific Head

Fan Liu, Xiang Gu, Baoyu Lv, Chuanyi Zhang, Liang Yao, Yuye Ma, Yuhui Zheng

原文摘要

Aerial perception systems are increasingly expected to support diverse tasks, yet existing solutions remain fundamentally tied to task-specific outputs. Detection, segmentation, and other perception objectives are usually learned either by separate models or by sharing a backbone with multiple task heads, leaving the model itself unaware of the common structure underlying these tasks. We are interested in asking: can a single perception representation support different levels of understanding without being designed for any specific task? We notice that occupancy is a promising task-agnostic representation for drone perception. By modeling the spatial existence and semantics of the environment, it naturally bridges different perception granularities, from coarse scene understanding to fine-grained object localization. Therefore, we introduce AerialOcc, a unified occupancy-based perception model that enables multiple drone perception tasks from a single inference process, without maintaining task-specific prediction heads. To facilitate this direction, we construct AerialOcc-20K, a large-scale multi-class occupancy dataset for aerial environments. Extensive experiments show that AerialOcc achieves competitive performance across diverse perception tasks while preserving a unified architecture. Our findings demonstrate that occupancy can serve as a universal perception interface, offering a new perspective toward flexible and scalable visual intelligence for autonomous drones from a common 3D scene representation. Models and data are publicly available at https://github.com/guxiang2002/AerialOcc

cs.CV

新论文 · v1arXiv:2611.22314

Inertial Video World Models

Yuan Gao, Fan Xu, Yu Guo, Yuxu Lu, Zhengru Fang, Hao Wu, Xiaomeng Huang

原文摘要

The physical world has inertia: it evolves from what already exists rather than being recreated at every instant. However, many existing video world models lack an explicit mechanism for inertial state evolution, leaving the continuity of motion and structure implicit in video prediction. During autoregressive rollouts, repeated reconstruction can accumulate errors and destabilize the predicted dynamics. To address this limitation, we introduce InertialWorld, an Inertial Video World Model that makes inertia a structural prior for autoregressive prediction: existing scene evidence is carried across time rather than reconstructed at every step. Central to this formulation is Inertial Memory, which turns memory from passive predictive context into an evolving video state with two complementary views: a dense Eulerian grid preserves scene-aligned evidence, while persistent Lagrangian carriers bind local content to learned canonical coordinates. At each step, the model transports the carrier content according to action-conditioned motion, predicts the complete next video state from the transported carriers and dense grid, and uses a learned gate to combine transported and newly predicted content into the memory for the next step. Extensive experiments across multiple domains, including robot manipulation, 3D game simulation, and open-world navigation, demonstrate that InertialWorld achieves competitive autoregressive prediction performance against strong video world model baselines. Codes link: https://github.com/YuanGao-YG/InertialWorld

cs.CV

新论文 · v1arXiv:2611.22312

Zero-Dimensional Attention Topology for Linguistic Acceptability

Saeed AlMarri

原文摘要

Topological summaries of Transformer attention provide sentence representations for linguistic acceptability classification. We examine a zero-dimensional persistent-homology ($H_0$) representation that summarizes minimum-spanning-tree merge values from 144 symmetrized BERT attention graphs into 1,440 features. The retrospective evaluation uses 8,517 downstream training sentences and 521 in-domain and 497 out-of-domain CoLA validation sentences after data-integrity filtering. The recorded out-of-domain Matthews correlation coefficients are 0.438 for the topological representation and 0.508 for attention statistics, compared with 0.545 for BERT. Attention-feature results are retained aggregate measurements; BERT predictions are rescored and length controls are refitted from the accompanying records. Analytical results show that the representation retains token-count information and discards a class of directional attention differences. Source resampling of BERT predictions also demonstrates the sensitivity of uncertainty estimates to the sampling unit. The reported results do not demonstrate a predictive advantage for this fixed topological representation over simpler attention summaries. They identify representation properties and evaluation controls relevant to subsequent studies of attention topology.

cs.CL · cs.LG

新论文 · v1arXiv:2611.22310

EviDARL: Evidence-Centric Dual-Agent Reasoning via Alternating Reinforcement Learning for Multi-Table Question Answering

Dunhan Li, Leilei Gan, Lirong Gao, Wenyan Fan, Yongwei Wang, Sheng Guo, Fei Wu

原文摘要

Despite advances in LLM-based table reasoning, most studies focus on single-table settings. Multi-table QA requires multi-hop reasoning over complex table relationships and evidence dispersed across long contexts, often without verifiable intermediate traces. To address these challenges, we introduce EviDA, an evidence-centric dual-agent framework comprising an Evidence Construction Agent and a Reasoning and Answering Agent. The Evidence Construction Agent generates and executes table-manipulation programs over complete tables to produce question-specific evidence and verifiable intermediate traces, simplifying subsequent reasoning. The Reasoning and Answering Agent then performs multi-hop reasoning over this evidence to derive final answers. We further introduce EviDARL, which combines agent-specific fine-grained rewards with parameter-efficient alternating reinforcement learning to improve collaboration between the agents. By optimizing each agent in turn while holding the other fixed, EviDARL enables bidirectional adaptation between evidence construction and answer reasoning. Experiments on MMQA and TQA-Bench demonstrate that EviDARL substantially outperforms competitive open-model and multi-table reasoning baselines under constrained model and training budgets.

cs.AI

版本更新 · v4arXiv:2607.27287

Alternating Abduction and Planning over Temporal Dynamic Knowledge Graphs

Amir Hossein Sharafi, Alireza Shahbazi

原文摘要

Knowledge graphs change over time, but the effects of actions on them are only partly stated: the ontology entails further consequences, facts that an action needs are often unknown, and an action may make the graph inconsistent. We study these problems for Temporal Dynamic Knowledge Graphs (TDKGs), that is, SROIQ knowledge bases whose actions are rules with delete/insert templates and whose events lie on an intrinsic timeline. We present three tools: temporal projection, the exact test of plans; DDA (Direct-Derivation Abduction), which explains an observation by assuming its negation and negating what the reasoner newly derives; and APT (Abduction and Planning over TDKGs), which plans backwards from a goal, assumes the facts that the plan needs but nobody stated, and lets DDA explain the assumptions, each explanation becoming a sub-goal, up to a depth bound. The tools use a SROIQ reasoner only through a small contract, so they depend neither on a particular reasoner nor on a particular data structure; they are designed for a reasoner that processes added and removed axioms incrementally. Change is treated without modal operators, on one linear timeline and without possible worlds, so decidability of projection follows from that of SROIQ. We prove that indirect effects are exactly the entailments of the updated state, that DDA and APT are sound and terminate, and that bounded planning is 2NExpTime-hard and in 3ExpTime. We compare the tools with hitting-set abduction, the solver CATS and classical planning, and run them on six benchmarks and five reasoners with identical results.

cs.AI · cs.LO

新论文 · v1arXiv:2611.22309

Efficient Wide-Beam Generative Retrieval with Model-Native Trie Decoding and Shared-Context Attention

Vedant Jhaveri, Arashpreet Singh Mor, Satyam Kumar, Alex Tsun, Qing Lan, Shaunak Mishra, Sriram Vasudevan

原文摘要

Generative retrieval (GR) predicts catalog entries as short semantic identifiers (SIDs). Trie-constrained beam search keeps these identifiers valid, but wide beams expose two serving costs: vocabulary-wide score tensors that are mostly discarded, and repeated attention over the same prompt. We present Trie-Head, a model-native output interface that stores the identifier trie as validated GPU tensors. Compared with a Python custom logit processor (CLP), it reduces CPU--GPU coordination and memory traffic by avoiding Python constraint callbacks and vocabulary-wide candidate buffers. It scores compact codebook candidates and streams the full-vocabulary normalizer, preserving the original model's valid-token scores in real arithmetic without retraining. Shared-context attention complements this output path by reusing prompt key/value blocks across beams while preserving their private decode tails. We implement both mechanisms in SGLang and evaluate candidate sourcing for LinkedIn Hiring Assistant and qualification retrieval for the Qualification Retrieval Platform. The combined system improves closed-loop throughput by up to 5.57x over the CLP baseline and up to 2.63x over BF16 FlashRec at a common beam width of 200 on the Qualification Retrieval Platform workload.

cs.AI

新论文 · v1arXiv:2611.22308

VRLLM: Turning LLMs into Powerful Tabular Classifiers

Yingtong Dou, Shubham Jain, Junpeng Wang, Hadi Abdullah, Vineeth Rakesh Mohan, Yuzhong Chen, Liang Wang, Yiwei Cai

原文摘要

Large Language Models (LLMs) have shown strong performance on text, but whether pretrained LLMs are effective for large-scale tabular classification remains unclear, as many previous works demonstrate that LLMs' tabular data classification performance falls behind tree-based models or neural architectures designed for tabular data. At Visa Research, we managed to fine-tune a pretrained Llama 3.2 1B LLM on billions of rows of labeled tabular data and make it outperform a wide array of tabular classifiers and even our competitive production deep learning model. For ease of reference, we refer to the model as the Visa Research LLM (VRLLM). In this paper, we share how we achieved this exciting result, covering data preparation, training recipe, ablation studies of design choices and deployment validation. We also benchmark frontier LLMs on the same task and analyze their prediction behavior across model families and generations. Our interpretability experiments suggest that VRLLM learns feature-specific predictive associations, while component ablations indicate that the earliest two FFN layers contribute to the emergence of linearly decodable task information. Our paper provides an engineering recipe and a focused empirical case study on adapting compact LLMs to industrial tabular prediction tasks.

cs.LG · cs.CL

新论文 · v1arXiv:2611.22307

Learning to Edit IFC Building Models: Verifiable Checkers as the Training Signal for Dependency-Aware Editing Agents

Jiaxin Zhang, Yao Luo, Yuze Dan, Yunqin Li, Bowen Wang

原文摘要

Editing a building information model in the Industry Foundation Classes (IFC) schema requires propagating changes to dependent elements while preserving unrelated entities. Existing language-model agents for IFC editing use prompted models without learning from edit outcomes. Target-file comparisons do not specify which alternative edits are allowed or which unrelated entities must remain unchanged. We present IfcGym, a CodeAct environment in which a language model edits IFC through executable code and four checkers verify validity relative to the input model, intent, dependency and preservation against a task specification. Their conjunction is strict success. IfcEdit distils verified teacher episodes into a Qwen3.5-9B student through supervised fine-tuning (SFT), then applies Group Relative Policy Optimization (GRPO) with strict success as the reward. On IfcEditBench, 1,990 editing tasks on 13 held-out real projects, the final student reaches 86.78% strict success, from 79.15% after SFT. The paired confidence interval for the difference from its teacher includes zero; the same recipe on a 27B model reaches 91.76% and exceeds the teacher. On the public benchmarks BIM-Edit and BIBIMBAP the final student scores 55.19 and 54.50. On IfcEditBench, the students outperform all prompted models except the teacher under matched tool access; both evaluated frameworks also score lower. Rewarding all four checkers yields 4.83 points more strict success than rewarding intent and validity alone.

cs.AI

版本更新 · v2arXiv:2611.21152

From Repositories to Training Environments: Scaling Long-Horizon Coding Agents with Environment Evolution Loop

Yang Tian, Tianyu Zheng, Xiyuan Yang, Yaxin Du, Chengran Yang, Bo Zhao, Jian Yang, Bryan Dai

原文摘要

Training coding agents for long-horizon tasks requires environments with verifiable feedback. Existing pipelines often follow a linear process that ends with validation, establishing usability but providing little guidance on improving training value. Recursive self-improvement (RSI) often requires model rollouts or model training followed by downstream evaluation, with costs and feedback delays amplified on long-horizon tasks. How can we use timely, reliable proxy signals to improve training value and synthesize environments at scale? We present RepoFactory, an automated pipeline that converts real repositories into verifiable environments where agents build complete projects from scratch given a language specification. Its Environment Evolution Loop optimizes a multiplicative objective combining validity, structural coupling, and implementation scope through proxy feedback. RepoFactory produces 10,159 environments across 17 software domains. Training Qwen3.5-35B-A3B on these environments yields RepoHorizen-35B-A3B, which achieves gains of 22.6 percentage points on NL2Repo-Bench and 8.5 points on average across five benchmarks covering long-horizon coding and agentic tasks in real-world production settings, compared with 17.5 and 6.4 points without environment evolution. These results highlight the training value of RepoFactory environments and the additional gains from the Environment Evolution Loop.

cs.CL

版本更新 · v5arXiv:2610.13357

ECGGuard: Deep Watermarking of Electrocardiogram Signals With Error-Correcting Codes

Kuan-Yu Chen, Kuan-Chen Wang, Yu Tsao, Jian-Jiun Ding

原文摘要

Wearable electrocardiogram (ECG) recordings pass through multiple networks and systems before automated interpretation, leaving patient metadata vulnerable to loss. Digital watermarking can embed this metadata in the signal, but conventional methods fail under time shifts, and high waveform similarity does not guarantee the same downstream diagnosis. We present \rev{ECGGuard}, a deep watermarking framework for single-lead ECG. A fully convolutional generator embeds the payload without signal quantization, a detector decodes the message frame by frame and checks for watermark presence, and during training a frozen arrhythmia classifier penalizes changes that would alter its predictions. Because high bit accuracy does not ensure whole-message recovery, the payload is protected by extended Hamming codes, \rev{a validation-selected channel ordering}, and soft-decision decoding. On the MIT-BIH Arrhythmia Database, \rev{averaged over three training runs, ECGGuard} keeps bit accuracy above \rev{98\%} under time shifts of 10 to 50 samples, where transform-domain baselines drop to chance. The coded 16-bit payload is recovered exactly in \rev{99.95\%} of clean segments\rev{, in over 96\%} under time shifts, 10\% sample deletion, or 10\% packet loss\rev{, and in 99.1\% for unseen subjects}. \rev{For the guiding classifier, the diagnostic loss limits the drop in ventricular-beat sensitivity to 1.6 percentage points on the test records (35.0 without it) and to 12.2 points for unseen subjects (67.0 without it); the drop grows to 10.3 points for independently trained classifiers, and the protection does not transfer to an external database.} \rev{ECGGuard} has 0.56 million parameters and needs about \rev{19}~ms per segment on a desktop CPU.

eess.SP · cs.CR · cs.CV