跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描:2026-11-22 06:41 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 08:35 — 2026-11-22 08:35(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 06:41最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

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

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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

找到 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 06:39(北京时间)
版本更新 · v2arXiv:2605.08553

VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation

Zichen Xie, Mrigank Pawagi, Yuxin Liu, Aaditi Rai, Lize Shao, John Berberian, Sicong Che, Wenxi Wang

原文摘要

Large language models can generate useful code from natural language, but their outputs come without correctness guarantees. Verifiable code generation offers a path beyond testing by requiring models to produce not only executable code, but also formal specifications and machine-checkable proofs. Progress in this direction, however, is difficult to measure: existing benchmarks are often small, cover only part of the pipeline, lack ground-truth proofs or rigorous specification validation, or target verification settings far from mainstream software development. We present VeriContest, a benchmark of 1,006 competitive-programming problems from LeetCode and Codeforces for verifiable code generation in Rust with Verus. Each problem includes a natural language description, expert-validated formal specifications, judge-accepted Rust code, Verus-checked proofs, and positive and negative test suites. VeriContest is constructed through a three-phase pipeline that scales from manually verified seed problems to semi-automated expansion with human-in-the-loop review. To strengthen benchmark quality, we also use testing to validate postcondition completeness. VeriContest supports both isolated and compositional evaluation of specification, code, and proof generation, and end-to-end verified program synthesis. Evaluating ten state-of-the-art models reveals a sharp gap between ordinary coding and verifiable code generation: the strongest model reaches 97.51% on natural-language-to-code generation, but only 57.16% on specification generation, 13.82% on proof generation, and 6.76% end-to-end. These results identify proof and specification generation as the central bottlenecks for current models and establish VeriContest as a rigorous platform for evaluating and training future systems that generate code with machine-checkable correctness.

cs.SE · cs.AI · cs.LG

版本更新 · v3arXiv:2602.13415

The Rise of AI Search: Implications for Information Markets and Human Judgement at Scale

Sinan Aral, Haiwen Li, Rui Zuo

原文摘要

We analyzed global, longitudinal AI and traditional search data to spark a conversation about the growth and impact of AI search, and discuss its policy implications for platforms, regulators, scientists and citizens. We executed 24,000 search queries in 243 countries, generating 2.8 million AI and traditional search results in 2024 and 2025. We found a rapid global expansion of AI search and key trends that reflect important, previously hidden, policy decisions by AI companies that impact human exposure to AI search worldwide. From 2024 to 2025, overall exposure to Google AI Overviews (AIO) expanded from 7 to 229 countries, with surprising exclusions like France, Turkey, China and Cuba, which did not receive AI search results. While only 1% of Covid search queries were answered by AI in 2024, over 66% of Covid queries were answered by AI in 2025---a 5600% increase signaling a policy shift on this critical health topic. Our results also show AI search surfaces significantly fewer long tail information sources, lower response variety, and significantly more low credibility and right- and center-leaning information sources, compared to traditional search, impacting the economic incentives to produce new information, market concentration in information production, and human judgment and decision-making at scale. The social and economic implications of these rapid changes in our information ecosystem necessitate a global debate about corporate and governmental policy related to AI search. We hope this discussion and the dataset released with this paper elevate the global dialogue on AI search and its impact.

cs.CY

新论文 · v1arXiv:2611.10958

Hybrid Source Code Change Impact Analysis

Katharina Stengg, Christian Macho, Martin Pinzger

原文摘要

Change impact analysis (CIA) helps developers identify code entities impacted by their initial changes. While several approaches for CIA were proposed, they still struggle with either low precision or low recall, thereby increasing manual effort for developers to verify the results. Furthermore, limitations in the used datasets and experimental setups can bias the results reported by many CIA approaches. In this paper, we first address the dataset limitations by manually labeling 1,931 changed code entities stemming from 263 commits of 22 open-source Java projects. Next, we introduce two variants of katIA, our code change impact analysis approach that combines static impact analysis with the reasoning capabilities of large language models (LLMs). The first variant uses a single prompt (katIA-SP) for refining an initial static impact set while the second variant uses three specialized agents (katIA-MA). The evaluation with our curated dataset shows that katIA-SP with Gemini 2.5 Flash achieved an F1-score of 22.4% when matching impacted entities by their fully qualified names (FQN) and 27.0% when matching them by their class and entity names (CE). The latter shows an improvement of 2.0 percentage points over the state-of-the-art. This score is further improved by katIA-MA which, using Gemini 2.5 Flash, yields an FQN-matching F1-score of 29.1% and a CE-matching F1-score of 33.3%. While these improvements come at the cost of increased median generation time from 0.570 s to 11.214 s and median token usage from 1,235 to 6,462 tokens, the improved performance justifies the additional cost. The comparison of three LLMs using katIA-SP finds that Gemini 2.5 Flash is the most consistent model. These results indicate that combining static impact analysis with LLM-based refinement, particularly with the multi-agent variant, can improve code change impact analysis.

cs.SE · cs.AI

新论文 · v1arXiv:2611.10956

Risk-Sensitive Reinforcement Learning for an Options Market Maker: An Empirical Study with Real S&P 500 Options

Jacky Chen, Ing-Haw Cheng, John Hull, Landis Li, Zissis Poulos, Justin Shi, Andreas Veneris, Zeyu Wang

原文摘要

Options market makers absorb client order flow and must hedge the resulting inventory risk under trading frictions. We study whether an option hedging reinforcement learning (RL) agent trained on historical market data outperforms three alternatives in tail-risk protection: (i) traditional delta hedging, (ii) simple hedge-ratio rules, and (iii) the same agent trained in simulated markets. Most RL hedging agents are trained in model-generated markets that do not capture the crashes and volatility regimes present in real data. We introduce an empirical replay environment using S&P 500 option data from 1996 to 2017 and compare against a matched geometric Brownian motion (GBM) environment, a stochastic-volatility (SABR) simulator, and a hybrid that values historical paths with Black-Scholes, all sharing the same portfolio mechanics, stochastic arrivals, costs, and test period. We train a distributional Twin Delayed Deep Deterministic Policy Gradient (TD3) agent and evaluate it out of sample over 2018-2023. The agent trained on empirical data reduces Conditional Value-at-Risk (CVaR) tail loss by 3.1% compared to delta hedging and outperforms every hedge-ratio rule chosen during the training period and every alternative training environment. The reduction reaches 8.9% in volatile and falling markets, but reverses to a cost of 7-10% in rising markets. Empirical training induces a state-dependent short net delta: the policy under-hedges negative-delta books, most strongly after prices have fallen. This tilt disappears with GBM training and is weaker with SABR or hybrid training. These findings suggest that exposure to historical market dynamics can materially change a tail-risk hedging policy, although the evidence rests on a single test path and the edge is regime-conditional.

q-fin.RM · cs.LG · q-fin.CP

版本更新 · v3arXiv:2603.29264

Linear Generator Networks for Nonlinear Partial Differential Equations

Shafayeth Jamil, Rehan Kapadia

原文摘要

Most physical systems are governed by nonlinear partial differential equations, yet the analytical tools that make linear systems transparent, such as eigenspectra, dispersion relations and modal decomposition, remain unavailable in nonlinear settings. We introduce Linear Generator Network-Koopman (LGN-KM), a neural operator that learns a nonlinear lift and a continuous-time linear generator for the lifted dynamics through the decomposition $L_k = S - D_k$, where $S$ is skew-symmetric (conservative coupling) and $D_k$ is positive-definite diagonal (mode-selective dissipation). The decomposition guarantees stability by construction and exposes the eigenstructure directly, making linear-systems analysis available on a nonlinear PDE. On 2D Navier-Stokes turbulence, the generator yields a complete multi-branch dispersion relation and models trained independently at viscosities $100\times$ apart learn the same coupling spectrum ($R^2 = 0.87$). The same architecture shows the corresponding diffusive damping on FitzHugh-Nagumo reaction-diffusion, and for pulse propagation in optical fibers, the oscillation frequencies of the learned generator match the fiber's dispersion relation, giving the group-velocity dispersion to within $3.1\%$ with no fitted constant. The architecture additionally enables long-horizon stability, $O(1)$ continuous-time evaluation, and physics-informed cross-regime model transfer.

cs.LG · physics.flu-dyn

版本更新 · v2arXiv:2610.39869

Incorporating Machine-Others: An Enactive Exploration of Human-LLM Interactions

Elena C. Cuffari, Marta Pérez-Verdugo, Xabier E. Barandiaran

原文摘要

New concepts based in interactional thinking are required to understand how humans are changed by relating to LLMs. Standard theories of technological impact upon users' autonomy are inadequate here, because this technology is capable of inducing linguistic interactions with humans in an unprecedented manner. Traditional theories of social cognition also fall short, because LLMs have neither autonomy nor minds nor sociality as such. And yet, humans interact, talk, and create with them. We base ourselves on enactive theory, particularly on the theory of Linguistic Bodies and recent developments of enactive accounts of AI, to explore how we make sense with machines. We argue that we incorporate machine-others in two ways: in the tool-like sense of incorporation as enabling particular skills, but also in the more linguistic and identity-tied sense of incorporating (and incarnating) LLMs' ways of languaging. However, LLMs are themselves excorporated and excarnated phantoms of our own languaging; we give a (machinic) body to our language. As such, we are not just incorporating machinic others; we are incorporating excorporated others. These conceptual advances draw a new map of our linguistic relation to LLMs, putting them in continuation with other forms of languaging involving other linguistic artifacts (e.g., religious books). We attend to some particular forms that this relation takes today, and how they may be impacting the autonomy and becoming of LLM-engaged humans. We introduce the idea of "susceptive sense-making" to characterize increased semiotic labour that is carried by the lack of friction that we sometimes encounter within these services.

cs.HC · cs.AI · cs.CY

新论文 · v1arXiv:2611.10952

Optimal Sampling and Transmission Policy for Information Freshness in Gossip Networks

Irtiza Hasan, Ahmed Arafa

原文摘要

We study the optimal sampling and transmission policies for a transmitter communicating with n gossiping receivers with the objective of tracking a source's status over time using a semantic freshness metric: Version Age of Information (VAoI). The transmitter observes the version changes in the source, and can acquire a new information version by paying a sampling cost. The receivers gossip, allowing information exchange among each other without direct transmission. Gossiping can save on transmission cost, but it may propagate stale version information, necessitating transmitter intervention. With imperfect communication links, we formulate an infinite horizon average cost Markov Decision Process (MDP) in order to jointly optimize receivers' VAoIs, sampling and transmission costs in a time slotted fully connected (FC) gossip network. We first solve the MDP using Relative Value Iteration (RVI) algorithm. Then, we prove that the sampling decision has a threshold structure in the transmitter VAoI. Further, under reliable gossiping links, we show that transmission and idling has an VAoI-difference threshold structure with minimum VAoI activation. Numerical results obtained using RVI show that the optimal policy consistently outperforms natural baselines. These results characterize how source sampling, direct transmission, and receiver gossip should be jointly coordinated for cost-aware semantic freshness in gossip networks.

cs.IT · cs.NI · eess.SP

新论文 · v1arXiv:2611.10950

Interpretable Cyber-Physical Attack Detection in Smart Grids: A Leakage-Controlled Multi-Testbed Evaluation of Fusion, Robustness, and Observability Limits

Muhammad Ridwanul Hoquea, Sarah Sharif, Reza Saeed Kandezy, Yaser Banad

原文摘要

Cyber-physical smart-grid detectors are typically treated as black boxes and validated exclusively on clean, temporally shuffled datasets, which risk overly optimistic performance claims. This work presents a multi-testbed evaluation study built around an interpretable, time-windowed fusion Random Forest, adopting the pessimistic result whenever evaluation protocols disagree. (i) On a public paired cyber-physical dataset, shuffled cross-validation is optimistic: macro-F1 falls from 0.96 to 0.88 +/- 0.06 under rolling-origin temporal evaluation. A topology-free graph convolutional network (GCN) serving as a control confirms that this lightweight model is competitive on these splits. (ii) The adaptive and adaptive-joint feature-space attacks, which are infeasible as realistic grid manipulations, degrade macro-F1 to 0.67 and 0.34, respectively. Adversarial training and randomized smoothing partially restore performance, and a physics-constrained evolution-strategy evasion on the IEEE 14-Bus testbed shows the same vulnerability pattern. (iii) On real IEC-104 traffic, the cyber view reliably catches structural attacks (recall of 0.87 to 0.98) but largely fails on semantic value manipulation (recall of 0.11 to 0.35). An observability taxonomy on the IEEE 14-Bus system reveals that stealthy false data injection defeats all three observation views. (iv) On a full AC weighted least-squares state-estimation testbed, a forecasting-aided temporal test is evaded by slow ramps precisely where a rate-invariant physics-manifold test sustains detection at a common 5% false-alarm target. A full end-to-end evaluation on IEEE 118-Bus confirms the ordering but bounds its strength: the manifold test detects every trial down to 0.05 degree/step and 0.48 at 0.02 degree/step, against 0.14 for the temporal test. All code and benchmarks are released.

cs.LG · cs.AI · cs.CR

新论文 · v1arXiv:2611.10949

Explicitly capturing demonstrator multi-modality for distillation into diffusion policies

Shao Yuan Chew Chia, Rebecca H. Jiang, Abhinav Agarwal, Andreas Hofmann, Leslie Pack Kaelbling, Russ Tedrake

原文摘要

The diversity of a distilled diffusion policy's outputs matters beyond how it impacts the policy's success rate. In particular, downstream applications like test-time search and policy improvement require exploration. Thus, we want to distill multi-modal demonstrators into diffusion policies which reproduce their conditional action distributions. Standard data collection for behavior cloning applies a sliding window to demonstration episodes, which pairs unique observation histories with actions. These datasets can be fit by a policy that is either multi-modal, or unimodal with high Lipschitz constant to capture a diversity of actions seen at nearby observation samples. Prior work finds that diffusion policies trained on sparse data learn the latter, memorizing one action per observation. We adapt vine sampling to behavior cloning data collection to resolve this ambiguity: at some states the demonstrator visits, query it $k$ times from exactly the same observation. On a synthetic task, we study how the number of actions per observation, $k$, affects the learned policy, and find that larger $k$ yields a policy that better matches the demonstrator's conditional distribution, including its multi-modality and diversity. On a 2D truck unloading task, vine sampling likewise leads to a policy closer to the demonstrator and substantially improves both best-of-$N$ and expert iteration performance.

cs.RO

新论文 · v1arXiv:2611.10947

Validating AI-Discovered Cloud Threats on Live Infrastructure: A Multi-Model, Multi-Cloud Study

Nicholas Pecka, Lotfi Ben Othmane, Renee Bryce

原文摘要

Cloud infrastructure threat modeling lacks empirical validation of AI-discovered threats. We present a three-phase methodology of multi-agent threat discovery, automated exploit synthesis, and non-destructive live validation, and apply it to three commercial foundation models on two cloud architectures, validating each threat natively on the cloud (AWS, GCP, or Azure) it was discovered against. Of 233 AI-discovered threats, 103 were confirmed and 34 refuted (75.2\% precision, 95\% CI [67.3, 81.7]); 44 were conditional (the named mechanism refuted but an equivalent impact shown through another path) and 52 indeterminate. Multi-model discovery helped through breadth, not agreement: the three models together found 2.2$\times$ the confirmed threats of the best single model at comparable precision, while threats reported by several models were confirmed no more often than single-model ones. False positives were not architecture-specific: they asserted access or system state the deployment did not have. Threats coded in advance as observable configuration resolved cleanly more often than multi-step behavioral threats (72.5\% vs.\ 51.6\%), which were more often conditional, suggesting that models more often misidentify the exploitation mechanism than the underlying weakness. AI-assisted discovery is a practical input to security workflows when paired with empirical validation.

cs.CR

新论文 · v1arXiv:2611.10945

CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs

Trong Khiem Tran, Minh Long Bui, Phi Le Nguyen, Mrinal Sen, Sanjay Srinivasan, Trong Nghia Hoang, Jana Doppa

原文摘要

This paper introduces COUPLED FLOW, a new neural operator learning framework for multi-physics PDE systems that captures the co-evolution of multiple physical processes by modeling their cross-process interactions. Unlike existing neural operator methods that primarily target single-physics settings, COUPLED FLOW employs a novel structure-constrained flow matching algorithm to learn process- specific mean velocity fields conditioned on the full multi-physics state. This enables fast and accurate one-step prediction of coupled PDE systems that would otherwise require expensive numerical simulations. A key challenge in training COUPLED FLOW however lies in sampling structure-constrained conditional flow interpolants that capture cross-process correlations and serve as training examples for flow matching. To address this challenge, we derive a multi-physics mean-flow consistency identity that characterizes cross-process interactions and defines the structure-constrained mean-flow matching loss. To provide informative training samples for flow matching with this loss, we develop a principled method for sampling correlated conditional interpolants based on posterior multi-output Gaus- sian processes, which capture richer cross-process correlations than the commonly used endpoint-conditioned linear interpolants. We also establish a theoretical re- sult showing that the Wasserstein-2 distance between the predicted and oracle PDE solution distributions is upper-bounded in terms of the structure-constrained flow matching loss and the smoothness of the learned flow. Experiments across diverse coupled PDE benchmarks demonstrate that COUPLED FLOW consistently outperforms existing state-of-the-art neural operators and generative PDE solvers.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.11523

NAVIS: Concurrent Search and Update with Low Position-Seeking Overhead in On-SSD Graph-Based Vector Search

Jaeyong Song, Hongsun Jang, Changmin Shin, Seongyeon Park, Yong Jae Ryoo, Seo Jin Park, Jinho Lee

原文摘要

On-disk graph-based vector search (GVS) has become the dominant approach for serving large-scale vector databases at high recall. Yet prior systems struggle to sustain concurrent search and update throughput on high-dimensional workloads. We identify the main bottleneck as position seeking, the graph traversal that finds neighbors during each update. Unlike search, which returns only the top-K closest vectors, it explores a much larger set to build an R-neighbor list of close neighbors and long-range shortcuts. These neighbors have different distance-accuracy requirements, yet search-oriented packed layouts fetch full vectors with every edge-list access, consuming cache capacity regardless of their role. We present NAVIS, an on-SSD GVS system that redesigns position seeking around this mismatch. At its core, locality-driven decoupling separates vectors from edgelists and packs graph-local edgelists together. This decoupling enables convergence-aware speculative reranking to selectively load full vectors until a sufficient set of close neighbors is resolved, while selecting the remaining shortcuts using approximate distances. It also allows NAVIS to devote cache capacity entirely to edgelists. To make this cache effective, NAVIS keeps the entrance graph fresh via lightweight updates that reuse traversal information already produced during position seeking, thereby maintaining a stable hot set of edgelists near its entry points. Across multiple large-scale benchmarks, NAVIS improves insertion throughput by up to 3.97x and concurrent search throughput by up to 4.00x while reducing search latency by up to 75.69%.

cs.DC

新论文 · v1arXiv:2611.10940

Semantic Synthesis over Brute-Force Search: LLM-Guided Transformation Design for Efficient Learning

Usha Shrestha, Radu Timofte, Dmitry Ignatov

原文摘要

Data transformation pipelines shape the training distribution in computer vision, but designing them is a computationally expensive problem. We investigate whether large language models can enable efficient discovery by synthesizing executable transformation programs outside predefined augmentation spaces. We compare nine strategies under a unified training protocol, including standard augmentation policies, brute-force search, direct code generation with two LLMs, and performance-guided generation using LLMs fine-tuned on accuracy-ordered transformation pairs. When the best candidates are retrained for 20 epochs, LLM-generated transformation programs lead on every dataset, reaching 0.8877 accuracy on CIFAR-10, 0.5825 on CIFAR-100, and 0.9588 on SVHN, surpassing brute-force search over 6,000 candidates. The best transform on CIFAR-10 and SVHN comes from a fine-tuned generator using 270 candidates, while the best on CIFAR-100 comes from an off-the-shelf generator using only 10. This needs 22x fewer candidate evaluations in the generation step and 600x fewer for off-the-shelf generations, relative to brute-force search. Beyond transformation discovery, we analyze the reliability of the reduced-budget evaluation commonly used for augmentation search. Correlating one-epoch selection scores with 20-epoch outcomes reveals strong, weak, and absent predictive relationships depending on the dataset and architecture, with correlations ranging from 0.756 to near zero. A positive control indicates that range restriction alone is unlikely to explain the low correlations. Our results indicate that semantic synthesis with code LLMs provides an efficient alternative to search-based transformation discovery and highlight the importance of validating evaluation fidelity when optimizing data transformations.

cs.CV · cs.AI

版本更新 · v2arXiv:2609.03102

WireSeg-32K: A Physics-Grounded Synthetic Dataset for Wire Instance Segmentation

Zilin Dai, Lehong Wang, Yi Yang, Xiang Fei

原文摘要

Deformable linear objects such as wires and cables are difficult to segment because they are thin, highly deformable, and frequently self-occluded, while large-scale instance-level annotations are expensive to obtain in real scenes. Existing resources either focus on cable tracing or semantic segmentation under constrained settings, or generate visually plausible images without physically grounded wire deformation. We present WireSeg-32k, a synthetic dataset for wire instance segmentation with 32,000 RGB images, instance masks, depth maps, and a complementary real-world test set with annotations. To generate this dataset, we develop DeformX, a co-simulation pipeline that couples Cosserat-rod dynamics with photorealistic Isaac Sim rendering, enabling physically plausible, contact-consistent wire shapes, CAD-based wire assets, and diverse visually grounded scenes. As a simple baseline, LoRA fine-tuning SAM3 on WireSeg-32k alone improves real-world mAP@75 by 10.2% over the off-the-shelf model, showing that physically grounded synthetic data can transfer to real wire perception.

cs.CV

新论文 · v1arXiv:2611.10938

BRACE: Belief-guided Residual Adaptive Control for Safe Navigation under Unknown Disturbances

Jaeyoun Choi, Niklas Schmid, Oswin So, Augustinos Saravanos, Chuchu Fan

原文摘要

Disturbances encountered during autonomous navigation generally vary across space, often discontinuously, as obstacles redirect wind and changing terrain alters traction. Tracking controllers typically assume sufficient control authority to mitigate disturbances and maintain safety; the regime where this assumption fails remains underexplored. We present Belief-guided Residual Adaptive Control (BRACE), a hierarchical reinforcement learning (RL) framework for reach-avoid navigation under unknown, bounded, spatially varying disturbances. BRACE infers a disturbance belief from model prediction errors and uses that to condition a high-level policy that adapts the reference trajectory. The policy combines a nominal and a belief-guided residual term, trained jointly with a likelihood-ratio advantage reweighting heuristic. We evaluate BRACE in three simulated quadcopter environments with abruptly switching wind fields, and validate it on Crazyflie hardware with fan-generated disturbances. Across these settings, BRACE improves reach-avoid performance over model predictive control and RL baselines.

cs.RO · eess.SY

版本更新 · v4arXiv:2604.17299

Cat-DPO: Category-Adaptive Safety Alignment

Tiankai Yang, Yi Nian, Xinyuan Li, Ruiyao Xu, Henry Peng Zou, Kaize Ding, Xiyang Hu, Yan Liu 等 9 位作者

原文摘要

Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones. Most preference-based safety alignment methods collapse safety into a single scalar that is applied uniformly to every preference pair. The result is a model that appears safe on average but remains relatively unsafe in a minority of harm categories. We cast safety alignment as a per-category constrained optimization problem and derive Cat-DPO, a direct-preference-optimization algorithm with a separate adaptive safety margin for each harm category. The margin tightens when the model still produces unsafe responses in a category and relaxes once the model catches up, so the training signal tracks each category's current difficulty rather than averaging across a single global rate. Across two LLM backbones and six preference-learning baselines, Cat-DPO improves aggregate helpfulness and harmlessness and compresses per-category safety variance and the best-to-worst gap, offering a drop-in per-category refinement of direct preference safety alignment.

cs.CL · cs.AI

版本更新 · v3arXiv:2602.22586

TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion

Donghong Cai, Jiarui Feng, Yanbo Wang, Da Zheng, Yixin Chen, Muhan Zhang

原文摘要

Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy. However, real-world tabular datasets increasingly contain free-form text fields (e.g., reviews or clinical notes) alongside structured numerical and categorical attributes. Generating such heterogeneous tables with joint modeling of different modalities remains challenging. Existing approaches broadly fall into two categories: diffusion-based methods and LLM-based methods. Diffusion models can capture complex dependencies over numerical and categorical features in continuous or discrete spaces, but extending them to open-ended text is nontrivial, since they model each column as a continuous value or one of a closed set of categories, whereas text lives in an exponentially large sequence space. In contrast, LLM-based generators naturally produce fluent text, yet their discrete tokenization can distort precise or wide-range numerical values, hindering accurate modeling of both numbers and language. In this work, we propose TabDLM, a unified framework for free-form tabular data generation via a joint numerical-language diffusion model built on masked diffusion language models (MDLMs). TabDLM models textual and categorical features through masked diffusion, while modeling numerical features with a continuous diffusion process through learned specialized numeric tokens embedding; bidirectional attention then captures cross-modality interactions within a single model. Extensive experiments on diverse benchmarks demonstrate the effectiveness of TabDLM compared to strong diffusion- and LLM-based baselines. Our code is available at https://github.com/ilikevegetable/TabDLM.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.10936

Can small transformers learn the language of Coxeter groups?

J. Elisenda Grigsby, Yiyao Huang, Arushi Katyal, Ryan Lin, Pranav Ramakrishnan, Weiya Wang

原文摘要

The field of mechanistic interpretability is well-suited to collaborative projects between mathematicians and AI researchers. This work describes one such project. We trained a small transformer to learn the language of the Coxeter group affine A2, best known as the symmetries of the tiling of the Euclidean plane by equilateral triangles. We then formulated and proved a word-theoretic conjecture about affine A2 after observing the attention patterns of the trained model.

cs.CL · cs.LG · math.GR · math.RT

版本更新 · v2arXiv:2605.09654

Metropolis-Adjusted Diffusion Models

Kevin H. Lam, Tyler Farghly, Christopher Williams, Jun Yang, Yee Whye Teh, Arnaud Doucet

原文摘要

Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy for reducing this bias is to apply corrector steps based on the unadjusted Langevin algorithm (ULA) at each noise level within a predictor-corrector framework. However, ULA is itself a \emph{biased} sampler, as it discretises a continuous diffusion process. In this work, we consider \emph{adjusted} Langevin correctors that employ Metropolis--Hastings (MH) or Barker's accept-reject steps to correct for this bias. Since the target density ratio typically required by MH-based algorithms is unavailable, we propose methods that instead utilise the score function to compute the correct acceptance probability. We introduce the first exact method for adjusting Langevin corrections in diffusion models, based on a two-coin Bernoulli factory algorithm. We also propose an efficient approximation based on Simpson's rule that achieves accuracy of order $5/2$ in the step size at near-zero marginal cost. We demonstrate that these procedures improve sample quality on both synthetic and image datasets, yielding consistent gains in Fréchet Inception Distance (FID) on the latter.

stat.ML · cs.LG · stat.CO

新论文 · v1arXiv:2611.10931

Gendered Misclassification from Surname-Based Race Imputation

Noah Dasanaike

原文摘要

Researchers increasingly estimate political behavior based on race and gender from voter files, where race is imputed from surnames and geography. This only works where surnames suggest group membership, an assumption violated where surnames follow norms around marriage. Imputation is therefore biased against women who adopt their husband's surname, especially those who racially inter-marry, an outcome itself endogenous to partisanship. Using six US states recording self-reported race, I show that imputation is less accurate for Asian and Hispanic women, particularly those sharing the surname of a partner of another race, who differ politically from other women of their race. This violates assumptions behind downstream inference approaches, which nearly double the gender gap in partisanship among Asian voters. I derive an expression showing the bias is largest where a group is small. Using maiden rather than marriage-adopted surnames in North Carolina raises accuracy up to fourfold for women married across racial lines. Recovering maiden surnames, or omitting the married surname, removes much of the bias. In a national replication of a study of gender gaps in turnout, the correction more than triples the gap among Asian voters. In Lebanon, where wives register in their husband's locality, the error enters through geography.

cs.CL · stat.AP

新论文 · v1arXiv:2611.10930

Beyond Host-Side Control: HBM Controller Partitioning Across Host and HBM Base Dies

Tharunya Yogananda, Wantong Li

原文摘要

Recent generations of high bandwidth memory (HBM), such as HBM4, allow the base die of the memory stack to be manufactured using a logic process that can accommodate more complex controller functions next to the DRAM. We present the first systematic quantitative study of function-level controller placement between the host and the HBM4 base die on a silicon interposer. We divide the controller into its main functions and evaluate four placements, from a complete host controller to a complete base die controller, with intermediate placements that move maintenance or scheduling to the base die. We extend Ramulator 2 with HBM4 timing and maintenance, model a die-to-die (D2D) link with timing checks at the DRAM interface, and compose area, energy, and temperature from synthesized controller blocks, modeled storage, and interface data. A provisioned D2D link preserves per-stack bandwidth and adds about twice its one-way delay to unloaded latency. Maintenance moves to the base die with no bandwidth cost and frees host command slots, and the freed share grows with stack height. Replacing the wide interface with a D2D link saves 61% of host shoreline and 16.85 mm2 of host area per stack. The D2D link dominates the added base die area and power, and the base die runs cooler under streaming with link energy below 0.4 pJ/bit. Shared control delivers up to 1.72x the throughput of static partitioning between two requestors.

cs.AR

版本更新 · v3arXiv:2504.08897

On the Adversarial Robustness of Spiking Neural Networks Trained by Local Learning

Jiaqi Lin, Abhronil Sengupta

原文摘要

Recent research has shown the vulnerability of Spiking Neural Networks (SNNs) under adversarial examples that are nearly indistinguishable from clean data in the context of frame-based and event-based information. The majority of these studies are constrained in generating adversarial examples using Backpropagation Through Time (BPTT), a gradient-based method which lacks biological plausibility. In contrast, local learning methods, which relax many of BPTT's constraints, remain under-explored in the context of adversarial attacks. With the increasing real-world deployment of local learning methods in SNNs, it is critical to investigate whether these approaches introduce adversarial vulnerabilities that could compromise reliability. To address this problem, we examine adversarial robustness in SNNs through the framework of four types of training algorithms. We provide an in-depth analysis showing that direct gradient-based attacks are ineffective for locally trained models. To overcome these limitations, we introduce a hybrid adversarial attack paradigm that leverages the transferability of adversarial instances. The proposed hybrid approach demonstrates superior performance, outperforming existing adversarial attack methods. Furthermore, the generalizability of the method is assessed under multi-step adversarial attacks, adversarial attacks in black-box scenarios, and within the non-spiking domain.

cs.LG · cs.CR · cs.NE

版本更新 · v2arXiv:2609.38242

A Calculus for Units of Measure with Conversion

Eric Allen

原文摘要

Programs that compute with physical quantities often need to convert between units of measurement, and as the Mars Climate Orbiter showed, these conversions can be a rich source of errors. Meanwhile, typed unit calculi, our most rigorous formalisms for checking physical units in a program, have excluded unit conversions. Through this exclusion, they have established a powerful property: well-typed programs are invariant under rescaling (no program can depend on how big a meter is). But losing the ability to convert between units is a significant cost. In contrast, practical languages provide conversion but no invariance theorem. We present $Λ_S$, a typed lambda calculus with conversion, quantification over units and dimensions, and vectors and linear maps with per-component units, and we determine exactly how much invariance survives conversion. For terms without unit constants we prove two abstraction theorems: (i) a convert-free term is invariant under every rescaling; (ii) a term with conversions is invariant under every rescaling that scales all units of one dimension by the same factor. The condition in (ii) cannot be weakened: under any other rescaling, some conversion of a nonzero value is not invariant. For first-order programs, a verified decision procedure returns one of three verdicts: it certifies that no error in the declared conversion factors can change the program's answer, names the accumulated ratio through which such an error would scale it, or declines. A verified checker decides whether unit declarations are consistent and determine every conversion factor, and extracts each factor exactly. We also prove adequacy, erasure, and the $n$-variable Pi theorem of dimensional analysis with conversion. Every theorem is mechanized in Lean 4, and the evaluator compiles to a native binary.

cs.PL · cs.LO

版本更新 · v3arXiv:2608.26495

Video-FLAIR: Not Whether to Reason, But How

Yogesh Kulkarni, Pooyan Fazli

原文摘要

Multimodal queries can require different types of reasoning. Some can be answered via perceptual reasoning, extracting information directly from the visual signal, while others require compositional reasoning that combines observations or deliberative reasoning that evaluates competing hypotheses. However, many existing methods apply a uniform reasoning strategy across queries, leading to unnecessary computation on simple tasks and insufficient reasoning on complex ones. We introduce Video-FLAIR, a training framework that learns to select the appropriate reasoning mode for each query using reinforcement learning. During training, the model generates responses under all three modes for the same prompt, enabling direct comparison. A composite reward compares these responses to favor the most effective one based on correctness, grounding, and cost, while discouraging unsupported or misaligned deliberation. This yields a supervision signal for learning adaptive reasoning without per-query annotations. Video-FLAIR improves accuracy over the Qwen2.5-VL base model by +5.4 on MathVista, +4.8 on Video-Holmes, and +4.8 on Video-MMMU, while reducing average token usage to 95 compared to 417 for always-thinking baselines.

cs.CV

版本更新 · v5arXiv:2601.22888

DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English

Jio Oh, Paul Vicinanza, Thomas Butler, Steven Euijong Whang, Dezhi Hong, Amani Namboori

原文摘要

More than 80% of the 1.6B English speakers do not use Standard American English (SAE), yet LLMs often fail to correctly identify non-SAE dialects and generate stereotyped responses for their speakers. We introduce DialectLLM, the first large-scale framework for generating high-quality multi-dialectal conversational data encompassing the three pillars of written dialect---lexical (vocabulary), orthographic (spelling), and morphosyntactic (grammar) features. DialectLLM produces a dialect-parallel dialog dataset spanning nine English dialects. Partnering with native linguists, we design and validate SAE-to-dialect transformation rules, ensuring authenticity. Our approach challenges the prevailing practice of applying a single morphosyntactic feature set to both user utterances and model responses, showing that models should not reproduce up to 90% of the grammatical features of a dialect. Human evaluation confirms data quality, with annotators preferring DialectLLM over prior methods in 98.8% of pairwise comparisons for dialect naturalness. We then construct DialectLLM-Bench, a dialect-parallel benchmark with 50k+ dialogs, resulting in 97k+ QA pairs, and evaluate 17 LLMs on dialect identification and response generation tasks. Even frontier models achieve around 70% accuracy, fail to reach 40% for prominent dialects like Canadian English, and systematically misclassify non-SAE dialects as American or British. Beyond benchmarking, we show that DialectLLM data also serve as a scalable LLM post-training resource, suggesting a practical path toward dialect-aware conversational AI.

cs.CL · cs.AI

新论文 · v1arXiv:2611.10922

A Tool for Anonymized Clinical Knowledge Retrieval and Speaker Interaction Analysis of Healthcare Tele-mentoring Sessions

Parthaw Goswami, Erfan Zareei, Amy Vogelsmeier, Dima Dandachi, Ben Casterline, Mirna Becevic, Praveen Rao

原文摘要

We present a tool for anonymized retrieval of clinical knowledge and analysis of multi-speaker interactions in tele-mentoring sessions of Project ECHO (Extension for Community Healthcare Outcomes). Our tool's novel design includes: (a) a compound metadata filter that enforces strict speaker- and session-level isolation during retrieval, preventing cross-session context contamination; (b) MedGemma-4B as a locally-hosted language model for clinically grounded answer generation across three query modes; (c) interaction graphs to compute betweenness centrality, PageRank influence, and turn-taking patterns to quantify participation equity; and (d) a consistent alias-based anonymization scheme that prevents real participant names from appearing in any rendered output. During the demo, a healthcare provider (user) will interactively query multi-year ECHO sessions, explore participation dynamics through interaction graphs, compare sessions side-by-side, and assess answer quality via six reference-free RAG metrics, all without any cloud API dependency.

cs.IR

新论文 · v1arXiv:2611.10917

Remembering to Reason: Structured Memory for Scene and Workflow Understanding in Robot-Assisted Surgery

Zhiran Zhang, Hu Wang, Yichen Wu, Yutong Xie

原文摘要

Surgical video understanding is an important foundation for intelligent assistance in robot-assisted surgery. Similar surgical views can reflect different actions or procedural stages. Interpreting these views requires access to earlier observations, yet frame-centric prompting leaves this history unavailable. We introduce MemSurg, a framework that remembers surgical observations before reasoning over them. Its structured memory graph stores timestamped entity categories, locations, motion cues, and interaction summaries. Chronological links preserve recent context, while entity-associated links connect recurring observations across the procedure. Task-adaptive retrieval then supplies evidence-grounded prompts for scene and workflow reasoning, supporting both frozen inference and memory-conditioned supervised fine-tuning. Evaluation on robot-assisted prostatectomy and two complementary surgical benchmarks shows a 10.43-percentage-point gain over SurgRAW with GPT-4o. Memory conditioning adds 6.52 points under matched Qwen3-VL-8B fine-tuning, and an inference-time plug-in adds 7.04 points to EndoChat. These results support structured memory as a reusable source of procedural evidence for surgical video understanding. Our code will be publicly released.

cs.CV

版本更新 · v2arXiv:2602.02412

Provenance Verification of AI-Generated Images via a Perceptual Hash Registry Using Merkle Patricia Trie and BK-Tree

Apoorv Mohit, Bhavya Aggarwal, Chinmay Gondhalekar

原文摘要

The rapid advancement of artificial intelligence has made the generation of synthetic images widely accessible, increasing concerns related to misinformation, digital forgery, and content authenticity on large-scale online platforms. This paper proposes a registry-based framework for verifying AI-generated images through a registry-based provenance mechanism. Each AI-generated image is assigned a digital fingerprint that preserves similarity using perceptual hashing and is registered at creation time by participating generation platforms. The Merkle Patricia Trie, provides prefix-based organization and cryptographic integrity of the registry structure, while Burkhard-Keller tree enable similarity search based on Hamming distance. Verification is performed when images are re-uploaded to digital platforms such as social media services, enabling identification of previously registered AI-generated images even after benign transformations or partial modifications. The proposed system does not aim to universally detect all synthetic images, but instead focuses on verifying the provenance of AI-generated content that has been registered at creation time. By design, this approach complements existing watermarking and learning-based detection methods, providing a platform-agnostic, tamper-evident mechanism for scalable content provenance and verification at the point of large scale online distribution.

cs.CR · cs.CY

版本更新 · v4arXiv:2605.01973

Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

Luo Ji, Qi Qin, Ningyuan Xi, Teng Chen, Qingqing Gu, Hongyan Li

原文摘要

Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, application of meta-learning on LLMs is also limited due to its complexity and scalability. In this paper, we activate the meta-signal of $β$ within the SwiGLU blocks, resulting in a meta-gating mechanism that adaptively adjusts the nonlinearity of FFN. A hypernetwork is employed which dynamically produces $β$ on textual conditions, providing meta-controllability on LLMs. By testing on different condition types such as task, domain, persona, and style, our method outperforms finetuning and meta-learning baselines, and can generalize reasonably on unseen tasks, condition types, or instructions. Our code can be found in https://github.com/AaronJi/MeGan.

cs.CL · cs.LG

版本更新 · v2arXiv:2609.26249

PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models

Xiaocheng Lu, Shuhan Guo, Ziyue Ma, Jie Zhang, Jian Liu, Jingcai Guo, Haoxuan Che, Song Guo

原文摘要

Diffusion language models (dLLMs), such as LLaDA and Dream, have become competitive with autoregressive (AR) LLMs in generation quality while supporting native parallel decoding. A standard acceleration strategy is block-wise decoding, where each forward pass predicts a block of length B and commits high-confidence tokens. Confidence-threshold commitment adapts which tokens are accepted, but a fixed B still constrains the prediction scope. Existing horizon policies use manually chosen sizes, volatility statistics, or candidate-boundary scores. We instead use the model's own per-step confidence: in-window confidence typically follows a context-dependent cliff, providing a direct signal for adapting the look-ahead horizon. In this work, we propose PACE-dLLM, which refits this parametric cliff periodically in closed form, sets the next horizon at a shared confidence anchor, and retains confidence-threshold token commitment. Under a saturated-yield abstraction with iid, policy-independent monotone profiles, the oracle horizon is the smallest attaining maximal per-pass yield and improves the asymptotic forward-pass rate when fixed blocks undershoot it with positive probability. On four reasoning and code benchmarks across two open-source dLLM backbones, PACE-dLLM achieves the best average accuracy among the evaluated decoders on both backbones, with average throughput speedups of 5.23x on LLaDA and 3.06x on Dream (up to 8.52x on LLaDA MATH) over the unaccelerated semi-AR baseline, advancing the quality-throughput Pareto frontier.

cs.CL