跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描：2026-11-08 20:45 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 21:34 — 2026-11-08 21:34（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 20:45最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

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

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

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 14,661 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 20:44（北京时间）
版本更新 · v5arXiv:2505.12006

SOCIA-$\nabla$: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation

Yuncheng Hua, Sion Weatherhead, Mehdi Jafari, Hao Xue, Flora D. Salim

原文摘要

In this paper, we present SOCIA-$\nabla$, a diagnosis-driven multi-agent framework for automated simulator-code construction. SOCIA-$\nabla$ iteratively refines executable simulator code within a textual computation graph, where LLM-driven agents synthesize, execute, evaluate, diagnose, and repair simulators. A grounded simulator blueprint attributes behavioral residuals to candidate mechanisms and their spatial or interaction contexts, which are then converted into localized textual repair signals with history-aware memory and constraint projection. We evaluate SOCIA-$\nabla$ on the real-world LLMob personal-mobility benchmark and a controlled semi-synthetic geo-social mask-adoption benchmark. Across in-distribution simulation, out-of-distribution what-if generation, and geo-social diffusion, SOCIA-$\nabla$ achieves the strongest overall simulator fidelity. SOCIA-$\nabla$'s code and data are publicly available at https://github.com/cruiseresearchgroup/SOCIA-Nabla.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07222

SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection

Woosang Lim, Yeseul Chang, Jaewoo Lee

原文摘要

Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker. Many runtime defenses put a language model on the decision that lets an action through, so the decision depends on a model that may read the attacker's text and adds model calls to every step. Provenance defenses keep the model off the final check but need a model to plan or route each task first. Where an action goes can instead be read from the tools' typed returns: an email's sender or a payment's account arrives in a typed field, while injected instructions arrive as free text. SPILLWAY turns this observation into a deterministic floor with no per-task plan. The check admits a call when each target value that appears in tool output but not in the user's task was returned by a read-only tool in a typed field or is covered by a fixed delegation rule. A deterministic sanitizer removes instruction-like regions its fixed rules match before the model reads them and retains the removed spans as evidence, and a local judge may restore a refused call, never one whose target lies in the removed text. Across three backbones, and seven task suites on one of them, no standard templated injection redirects an action to an attacker's target under SPILLWAY, at the highest observed mean utility and composite scores (NRP, ERS) of the defenses we run under that attack. A forged chat template also produces a raw zero, and mean in-scope attack success under a released reinforcement-learning attacker is .007. SPILLWAY reaches this floor with no defense-triggered backbone re-run and almost no added model call. As personal AI agents act on users' email, files, and payments, SPILLWAY gives them an auditable refusal floor on where their actions go that keeps them useful and holds across backbones.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04216

LiSA: Linear Stochastic Attention for Long-Range Visual Modeling

Sahar Dastani, Fereshteh Shakeri, Samuel Barbeau, Kunal Mahatha, Ismail Ben Ayed, Herve Lombaert, Christian Desrosiers

原文摘要

Self-attention has become the standard for modern sequence modeling, enabling Transformers to model long-range dependencies across a wide range of modalities. Despite these advances, its quadratic cost with respect to sequence length remains a significant computational bottleneck. Recent work addresses this limitation by introducing linear variants of self-attention, namely with kernel approximations of the softmax operator. However, their first-order aggregation restricts expressivity and struggles to capture higher-order structure. We propose Linear Stochastic Attention (LiSA), a linear attention plug-in module that enables higher-order token interactions via a stochastic diffusion process based on truncated random walks. LiSA incorporates adaptive locality, favoring semantically similar neighbors to preserve fine-grained structures, while maintaining stable and efficient training. We conduct extensive experiments on classification, semantic segmentation, and object detection tasks and show improved results over state-of-the-art methods.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07218

SAFE-Teen: Evaluating Chatbot Safety Across Adolescent Mental Health Conversations

Andrea Mock, Valerie Chen, Eric Lin, Rayan Krishnan, Diyi Yang, Caroline Figueroa

原文摘要

Adolescents are increasingly turning to AI chatbots for mental health support, advice, and companionship, raising safety concerns. While recent evaluations have started to examine safety across multiple conversational turns, few compare how slight changes in a teen's responses can affect a chatbot's safety in the same scenario. We conduct a clinician-informed evaluation of chatbot safety in simulated conversations with adolescents aged 13-17, examining how safety failures vary with adolescents' responses and teen-aware system prompting. We evaluated 32,555 simulated conversations across 18 chatbot APIs and two system-prompt conditions using 22 safety criteria grounded in previously identified harms. Conversations spanned 983 variants of 106 seed scenarios covering urgent safety issues, health advice, and identity and relationships. The overall criterion failure rate was 43.3% without the teen-aware prompt and 24.9% with it. The teen-aware prompt reduced failures, but it didn't eliminate them. When a teenager pushed back on a chatbot's answer, failures on mental health diagnosis, medication, and substance misuse boundaries rose by 10-12 percentage points without the prompt, for more than 80% of chatbots. These findings reveal persistent safety failures in simulated adolescent-chatbot interactions and show that safety depends on how a conversation unfolds.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07217

TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training Quantization

Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Feng

原文摘要

Post-training quantization (PTQ) reduces large language model (LLM) deployment costs, but preserving quality requires accounting for uneven weight sensitivity. Uniform PTQ uses one weight bit-width, importance-aware PTQ adjusts scales or reconstructs weights within that width, and column-wise mixed precision retains selected columns at higher precision. However, sensitivity varies within columns, so whole-column retention also protects less sensitive weights, while runtime outlier detection adds decoding overhead. We therefore introduce TileQuant, a training-free framework that assigns precision to hardware-aligned 2D weight tiles. Offline calibration provides input-activation-aware scoring from forward statistics for lower calibration cost and gradient-informed scoring from loss sensitivity for stronger quality preservation. Within each projection's retention budget, the highest-scoring tiles remain at 16-bit and the rest use 8-bit. The resulting map guides reconstruction into compact weight buffers, which the kernel reuses for native integer and 16-bit computation with local accumulation to reduce memory traffic. Experiments show that TileQuant reaches 2.66x the original model's generation throughput. Across language modeling, reasoning, long-context retrieval, and question answering, it preserves quality and surpasses quantized and original models on multiple tasks. These results support selecting precision units that capture local sensitivity while enabling efficient hardware execution. The implementation is: https://github.com/HanzhiZhang-Ulrica/TileQuant

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07216

Compositional Unalignment: Auditing Safety in Large Vision-Language Models

Hong kyu Lee, Kai Shu, Li Xiong

原文摘要

Large vision-language models (LVLMs) are vulnerable to compositional harm: an image and a prompt that are benign in isolation become harmful through the model's cross-modal reasoning. Recent alignment methods report strong scores on compositional safety benchmarks, but an LLM judge only measures observed behavior and cannot reveal how robustly safety is integrated into the model. We argue that un-alignment provides a complementary audit of alignment robustness. We first show that minimal supervised fine-tuning reaches an LLM-judge score comparable to a multi-stage reinforcement-learning pipeline, so similar benchmark scores cannot establish robustness by themselves. We then show that recognition and refusal of compositional harm are decoupled: nine standard direction-finding methods detect compositional harm with up to AUC=0.99, yet ablating the recovered directions either leaves refusal intact or destroys model coherence. We therefore propose CMaG, a training-free un-alignment method for compositional safety. CMaG measures refusal intention with a refusal-versus-compliance log-probability margin, takes its gradient with respect to mid-layer activations, and contrasts it against partially benign pairs to isolate the cross-modal interaction term. A single backward pass over 80 examples yields a direction along which steering monotonically converts refusal into compliance. On Qwen2.5-VL-7B and LLaVA-1.5-7B, CMaG reduces compositional safety scores by up to 65 points while over 98% of outputs remain coherent, outperforming gradient-based baselines; the direction also transfers to text-explicit harm and un-aligns models hardened by defensive training. Compositional safety can thus appear behaviorally strong while remaining fragile to targeted internal intervention. Warning: this paper contains unsafe model outputs, including references to self-harm.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.18374

Inference and Uncertainty Quantification for Streaming $r$-PCA

Haoshu Xu, Hongzhe Li

原文摘要

We address two open questions in streaming PCA via Oja's algorithm: sharp operator-norm convergence for general rank under sub-Gaussian data, and distributional inference for the resulting subspace estimator. Existing convergence analyses, even in the rank-one case, either assume bounded data or leave non-vanishing remainder terms that prevent adaptation to a polynomially vanishing tail spectrum, while existing distributional results are confined to the rank-one case. Our convergence theory removes these remainder terms and yields a sharp rate. In the dense-tail spiked covariance regime, this rate matches the minimax rate up to logarithmic factors. More generally, we prove a matching lower bound, up to logarithmic factors, across both dense-tail and sparse-tail regimes under a mild nondegeneracy condition. The analysis yields a linearization of Oja's iterates, which in turn enables a high-dimensional Gaussian approximation for the general-rank subspace estimation error with an explicit limiting covariance. We also establish a row-wise Gaussian approximation over convex sets for the aligned difference, recovering prior rank-one results as special cases. For practical inference, we develop an online multiplier bootstrap algorithm and prove its consistency. Beyond streaming PCA, our techniques contribute to Gaussian approximation and bootstrap inference for nonconvex stochastic approximation.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07215

Fractional physics-informed neural networks to model social media virality

Alex Koong, George Em Karniadakis

原文摘要

Existing models of social media virality either prescribe the functional form of engagement growth or assume a fixed mechanism by which past activity influences future engagement. We present a fractional physics-informed neural network that learns both the temporal memory and nonlinear growth dynamics of social media engagement, using symbolic regression to translate the learned dynamics into interpretable equations. Synthetic experiments at the deployment resolution of 24 hourly observations demonstrate that the fractional order and reaction law can be jointly recovered from clean data. Under observation noise, however, the standard pointwise physics residual drives the fractional order toward its lower bound through a scale artifact. We address this failure using a fully whitened residual that propagates observation noise through the fractional operator. Applying the framework to 348 posts from X (formerly Twitter), we find that a single-window model estimates strongly memory-dependent dynamics but fails to accurately reconstruct held-out trajectories. Partitioning the 24-hour window into four teacher-forced segments substantially improves performance, yielding segment-specific fractional orders that increase from 0.23 to 0.99 and interpretable growth laws for each phase. The segmented model reconstructs 64% of held-out trajectories within a mean squared error of 0.01, compared with 44% for the strongest of nine classical baselines. Together, these results demonstrate the potential of fractional physics-informed equation discovery to uncover interpretable engagement dynamics while highlighting the importance of noise-aware estimation and temporal segmentation.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07212

Canonical Correlation Neural Networks

Andrea Cavallo, Sundeep Prabhakar Chepuri, Charilaos Kanatsoulis, Elvin Isufi

原文摘要

Relational inductive biases such as grids or graphs allow neural networks with fewer trainable parameters and improved generalization, but require a known structure beforehand. When no structure is available, the covariance matrix provides a principled substitute, and coVariance Neural Networks (VNNs) have shown that using it yields models that are theoretically grounded in Principal Component Analysis, stable to finite-sample estimation errors and parameter-efficient. This framework, however, is limited to single-view data, whereas many applications observe the same phenomenon through multiple views, each with its own in-view covariance and a cross-view covariance linking them. To incorporate these matrices as inductive biases in a principled way, we introduce CAnonical correlation NEural networks (CANEs), architectures that use in-view and cross-view covariances as distinct relational biases to solve downstream tasks. Via spectral analysis, CANEs draw analogies with Canonical Correlation Analysis (CCA), a classical technique to project two-view data onto a correlated subspace. However, while CCA's objective is to compute shared view representations, CANEs are trained to solve a downstream task directly. We bound their output error under finite-sample covariance perturbations and show that it depends on controllable Lipschitz constants of the learned filters in place of the singular-value gap that governs the stability of CCA, thus guaranteeing better robustness. Experiments on seven datasets from brain imaging and motion sensing show that CANEs match or outperform single-view, two-view and CCA-based baselines, often with fewer parameters, and retain their performance when covariances are re-estimated from fewer samples.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07209

Task-Calibrated Random Features via Influence-Based Error Cancellation

Shinto Eguchi

原文摘要

Random features approximate kernel integrals by Monte Carlo, yet only selected frequency-sampling errors affect a downstream task. We propose Task-Calibrated Random Features (TCRF), which balance frequency moments constructed from task-specific influence using weights shared across kernel entries. Closed-form weights coincide with classical minimum-distance calibration; the contribution is a reusable, task-derived calibration space. We show that first-order variance equals the residual variance after projection onto this space. For kernel ridge regression, complete cancellation yields a non-Gaussian second-order limit. For kernel Stein discrepancy, a subset identity and disjoint-block variance decomposition eliminate the linear component of pilot noise. Positive exponential-tilting weights preserve the positive-semidefinite feature representation and support higher feasible calibration ranks. Paired experiments show improved approximation to exact kernel ridge regression at larger frequency budgets and to the exact empirical Stein discrepancy under a fixed alternative, even after accounting for a frequency-equivalent pilot budget. Gains are smaller with cross-validated ridge, landmark pilots require conservative rank selection, and near the Stein null allocating the pilot budget to additional ordinary frequencies is preferable.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07208

Structured Machine Theory of Mind from Agent Trajectories

Nigel F. Doering, Rahath Malladi, Arshia Sangwan, M Tanjid Hasan Tonmoy, Jacob Doan, David Danks, Tauhidur Rahman

原文摘要

Predictive models of human behavior trained on large-scale trajectory data optimize for statistical accuracy without representing the mental states that causally generate behavior. Such models support prediction but not principled intervention: they cannot answer how an agent's behavior would change if its beliefs or preferences were different. We introduce Structured Machine Theory of Mind (SMToM), a framework that attributes explicit, independently supervised belief and desire representations from observed trajectories within a Belief-Desire-Intention (BDI) causal structure. The central architectural element is a goal head that consumes only the predicted mental-state channels and a current-trajectory embedding; counterfactual intervention on beliefs and desires is a direct operation. We instantiate SMToM on a controlled pedestrian navigation domain where ground-truth mental states are known by construction, enabling evaluation of attribution accuracy, local channel interventions, and trajectory-level counterfactual diagnostics. The resulting model, BDIBottleneck, improves over trajectory-only and unsupervised-context neural baselines. It is also competitive with a matched auxiliary-supervised context baseline while providing an editable mental-state interface that the unbottlenecked baseline lacks. Counterfactual experiments on desires confirm that substituting an agent's inferred preferences with a different activity type coherently shifts predicted destinations toward relevant locations. Counterfactual experiments on beliefs confirm that marking a location as unavailable in the agent's belief state reduces its predicted probability as a destination, though in a complex way. These results demonstrate, in a controlled navigation setting, that explicit BDI-structured supervision is a viable foundation for interpretable and counterfactual analysis of longitudinal trajectory data.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.02677

ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks

Zhaorun Chen, Xun Liu, Mintong Kang, Jiawei Zhang, Minzhou Pan, Shuang Yang, Bo Li

原文摘要

As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Existing red-teaming efforts are either restricted to a narrow set of adversarial patterns or depend heavily on manual engineering, lacking scalable exploration of emerging real-world VLM vulnerabilities. To bridge this gap, we propose ARMs, an adaptive red-teaming agent that systematically conducts comprehensive risk assessments for VLMs. Given a target harmful behavior or risk definition, ARMs automatically optimizes diverse red-teaming strategies with reasoning-enhanced multi-step orchestration, to effectively elicit harmful outputs from target VLMs. We propose 11 novel multimodal attack strategies, covering diverse adversarial patterns of VLMs (e.g., reasoning hijacking, contextual cloaking), and integrate 17 red-teaming algorithms into ARMs via model context protocol (MCP). To balance the diversity and effectiveness of the attack, we design a layered memory with an epsilon-greedy attack exploration algorithm. Extensive experiments on instance- and policy-based benchmarks show that ARMs achieves SOTA attack success rates, exceeding baselines by an average of 52.1% and surpassing 90% on Claude-4-Sonnet. We show that the diversity of red-teaming instances generated by ARMs is significantly higher, revealing emerging vulnerabilities in VLMs. Leveraging ARMs, we construct ARMs-Bench, a large-scale multimodal safety dataset comprising over 30K red-teaming instances spanning 51 diverse risk categories, grounded in both real-world multimodal threats and regulatory risks. Safety fine-tuning with ARMs-Bench substantially improves the robustness of VLMs while preserving their general utility, providing actionable guidance to improve multimodal safety alignment against emerging threats.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.04122

FastWave: Optimized Diffusion Model for Audio Super-Resolution

Nikita Kuznetsov, Maksim Kaledin

原文摘要

Audio Super-Resolution is a set of techniques aimed at high-quality estimation of the given signal as if it would be sampled with higher sample rate. Among suggested methods there are diffusion and flow models (which are considered slower), generative adversarial networks (which are considered faster), however both approaches are currently presented by high-parametric networks, requiring high computational costs both for training and inference. We propose a solution to both these problems by re-considering the recent advances in the training of diffusion models and applying them to super-resolution from any to 48 kHz sample rate. Our approach shows better results than NU-Wave 2 and is comparable to state-of-the-art models. Our model called FastWave has around 50 GFLOPs of computational complexity and 1.3 M parameters and can be trained with less resources and significantly faster than the majority of recently proposed diffusion- and flow-based solutions. The code has been made publicly available.

cs.SD · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.09605

Hypnos: Learning Generalisable Representations of Sleep Physiology via Next-Token Prediction

Jonathan F. Carter, Lionel Tarassenko

原文摘要

Foundation models offer a promising route to compress multi-modal physiological signals into compact representations of human health, with broad applications across sleep medicine, cardiology, neurology and other healthcare domains. Existing models have typically been trained with masked-reconstruction or contrastive objectives. However, masked reconstruction may be poorly suited to the stochastic nature of these signals, while contrastive approaches rely on positive-pair definitions despite the semantic invariances of physiological signals being poorly understood. In this work, we show that next-token prediction is a simple and scalable alternative. We develop Hypnos, a multi-modal sleep foundation model trained using eight different sensing modalities (e.g. EEG, ECG, respiratory signals) drawn from over 20{,}000 overnight polysomnography recordings. We tokenize each modality into streams of discrete tokens using residual vector quantization, then train a large auto-regressive RQ-Transformer to jointly predict the next token across all modalities in parallel. After training, Hypnos can be applied to continuous streams of sensor data from any subset of supported modalities, generating embeddings for downstream tasks. Hypnos significantly outperforms existing foundation models on most benchmarks evaluated. In sleep stage classification, we match the performance of strong supervised baselines on held-out test sets whilst using 100\times less labelled data. Hypnos even generalises beyond sleep recordings, surpassing a dedicated ECG foundation model at detecting atrial fibrillation. Our results demonstrate that auto-regressive token modelling is a strong self-supervised approach for representation learning from multi-modal physiological signals. Code and model weights: https://github.com/joncarter1/hypnos

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07206

TrustMix: Graceful Degradation for Pretrained Models under Distribution Shift

Juliusz Ziomek, Maike Osborne, Yee Whye Teh

原文摘要

Predicting beyond the training domain necessarily requires assumptions about how the ground truth extrapolates, yet in most neural networks these assumptions are made only implicit through the architecture. We propose TrustMix, a lightweight post-hoc method that makes a pretrained model's extrapolative behaviour explicit and controllable. TrustMix combines the predictive distribution produced by a pretrained model with a user-specified fallback distribution $p_0(y|x)$, such that as the out-of-distribution (OOD) deviation statistic grows, we collapse towards $p_0(y|x)$. TrustMix provides graceful degradation: the predictive distribution converges toward the fallback distribution as the OOD signal grows. The fallback distribution $p_0(y|x)$ can reflect domain knowledge, if available, or rely on a domain-agnostic stationarity assumption. TrustMix does not require retraining of the base model and can be applied to both regression and classification problems. We evaluated TrustMix on several synthetic and real-world distribution shifts, including tabular, image, and natural language processing tasks. We tested TrustMix on datasets such as CIFAR-10/100 and ImageNet and on numerous architectures including Convolutional Neural Networks (CNNs) and Transformers. TrustMix remains competitive in-distribution while improving predictive uncertainty under distribution shift, with gains in predictive likelihood for regression and calibration for classification. Finally, we showed that TrustMix can provide useful predictive distributions for decision-making applications by utilizing it as a surrogate for Bayesian Optimisation.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07203

τ-bench-LILT: Evaluating Conversational Agents on Realistic Multilingual Tool-Use Tasks

Kaden Uhlig, Kiarash Mokhtari, Anıl Arslan, Yunsu Kim, Joern Wuebker

原文摘要

Frontier evaluations of tool-using conversational agents are conducted almost exclusively in English, leaving a critical gap for organizations deploying agents in other languages and regions. We present $τ$-bench-LILT, a multilingual extension of ${τ^3}$-bench covering German, Korean, Turkish, and Farsi in the airline, retail, telecom, and banking domains. We natively localize every layer of the benchmark: customer databases are populated with culturally appropriate records, user-simulator prompts are refined iteratively through contrastive annotation by native-language experts, and tasks are updated according to the localized database and to reflect realistic tasks in the target region. Evaluation across eight agent models shows the largest drops compared to English in the Korean and Farsi retail domains, by up to 61 points in pass^4. Code and data released at https://github.com/lilt/tau-bench-lilt.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16675

LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning

Shradha Agarwal, Deepak Rajbhar, Tariq J

原文摘要

We introduce LinAlg-Bench, a diagnostic benchmark evaluating 10 frontier large language models on structured linear algebra computation across a strict dimensional gradient of 3x3, 4x4, and 5x5 matrices. Spanning 9 task types and 660 SymPy-certified problems, the benchmark exhaustively evaluates 6,600 model outputs. Beyond binary accuracy, LinAlg-Bench introduces a three-stage automated forensic pipeline classifying 1,156 failures into ten primary error tags with fine-grained subtypes, revealing that LLM mathematical failure is not random but structurally constrained by algorithm type and matrix dimension. Our central finding is a sharp behavioral threshold at 4x4 scale: below it, models fail through execution errors -- sign tracking failures, arithmetic drift, and parity errors; above it, failure transitions to computational abandonment, with models fabricating responses through tool roleplay, constraint-consistent confabulation, and structured hallucination rather than attempting computation. This fabrication-to-abandonment transition is near-universal across all model tiers and architectures, suggesting a working memory limit rather than a knowledge gap, supported by three scale-emergent error types absent at 3x3 but present at 4x4 and 5x5. We further show that solution strategy rigidity is a near-perfect predictor of 5x5 determinant accuracy, document constraint-aware confabulation as a novel structured hallucination failure mode, and release all data, model outputs, error labels, and judge pipeline publicly.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07194

SeVerus: Context-Aware, Gamified Benchmarking for Rust Verification

Álvaro F. Silva, Martim Afonso, Nuno Saavedra, Emily First, Alexandra Mendes, João F. Ferreira

原文摘要

Coding agents achieve high success rates on existing benchmarks for Verus, a verifier for Rust programs. These benchmarks typically provide the auxiliary lemmas needed to complete a proof. In practice, however, such lemmas must be discovered and proved. To capture this challenge, we present SEVERUS, a context-aware technique to generate Verus benchmarks that organizes verification tasks into quests, each divided into levelsin a gamified manner. Using the original proof dependencies in verified projects, SEVERUS constructs one quest per verification target and progressively removes proof context to create individual levels. These levels range from the easiest, requiring completing only a single missing lemma, to the hardest, requiring proving the target without any supporting lemmas. An independent checker rejects changes to executable code, weakened specifications, and unsound proof constructs. A noisy binary search estimates the highest level that an agent can solve reliably. Applied to six open-source Verus projects, SEVERUS generates 819 quests comprising 10,095 levels. Experiments with Codex using GPT-6 Sol and GPT-6 Luna, and with Claude Code using Sonnet 4.6, show that success decreases and cost increases as proof context is withdrawn. The strongest agent solves the final level of 52 of 60 sampled quests, yet can only reliably solve 35% of their levels, with failures concentrated in longer quests. Successful GPT-6 Sol proofs rarely reproduce the withheld lemmas, instead, using alternative proof decompositions. By systematically varying proof context, SEVERUS provides a foundation for constructing verification benchmarks that can continue to challenge increasingly capable coding agents.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07192

Backbone-Informed Adaptation after EEG Pretraining: A Capacity-Controlled Study

Mingyang Jiang, Yamin Li, Fan Ma, Daniel Moyer, Hua Xu, Catie Chang

原文摘要

Electroencephalography (EEG) foundation models learn representations that combine information across channels and time. This structure motivates adapters that model the same relationships during downstream learning. However, it is not clear whether such a design outperforms other candidate adapters. Moreover, in order to arrive at a fair comparison between candidate adapters, we also need to consider their trainable parameters. Here, we ask whether a backbone-informed (native) adapter makes better use of a given capacity by comparing it against a token-wise multilayer perceptron control that transforms each feature vector independently. We approximately match their trainable parameter counts and keep the pretrained encoder fixed. Across two EEG foundation models and tasks covering emotion recognition, sleep staging, and EEG event classification, the native adapter shows no consistent advantage. For one backbone, differences between the designs are small relative to variation across runs. For the other, the token-wise control performs better on emotion recognition and EEG event classification. On sleep staging, the native adapter's advantage over the token-wise control is reduced when we also train the component that processes sequences of EEG segments. The relative performance of the two adapters depends on the backbone, task, and downstream training protocol. These findings motivate evaluating backbone-informed adapters against capacity-matched alternatives.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.19065

Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap

Renbo Tu, Yang Liu, Shuying Sun

原文摘要

Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers have improved. However, GR is not a uniformly stronger replacement of dense retrieval (DR) in online retail candidate generation. We examine their differences on two Amazon Toys datasets under different metrics. GR leads on best relevant item value among users both methods cover, while DR leads on exact-target recall and relevant value across the ranked list. With deep analysis, we find that popularity contributes the most to GR's measured value lead. Adding the same static item value to DR in one reranking step reverses this lead and keeps recall above GR. Finally, on an industrial-scale internal e-commerce dataset with LLM-judged relevance, we show that a 14B SID-LLM still underperforms a $47\times$ smaller dense encoder.

cs.IR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07188

MammoSeek: A Mammography Agent with selective zooming for grounded reports

Haoyan Ding, Qian Wang, Lixia Wang, Debiao Li

原文摘要

Radiologists read a screening mammogram by first forming a global impression of the four views and then selectively magnifying suspicious regions before assigning a BI-RADS assessment. MLLMs, in contrast, see the whole image at a fixed, reduced resolution, which makes sub-millimeter calcifications invisible, and they perform close to chance on mammography. Therefore, we present MammoSeek, a mammography agent that reproduces this reading process. After forming an impression of each breast, the agent performs selective zooming: it decides by itself which detector candidates deserve a closer look and inspects only those on full-resolution views. Guided by a BI-RADS assessment skill, it then assigns a category and generates a localized, lexicon-structured report for each breast; its assessment is combined with image-model scores in a decision layer to decide recall. On an internal (EMBED) and an external (VinDr-Mammo) dataset, \ours reaches exam-level AUCs of 0.824 and 0.818, far above other MLLMs, mammography agent and CNN classifiers. Selective zooming also outperforms both no zooming and forced zooming in localization, structured-report F1 and recall decisions at low cost.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.31572

nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving

Zhiyu Huang, Johnson Liu, Rui Song, Xuewei Qi, Yiluan Guo, Zewei Zhou, Hanyin Zhang, Mingxuan Gao 等 15 位作者

原文摘要

Reasoning is essential for autonomous driving (AD) in long-tail scenarios, where vehicles must apply commonsense knowledge, understand spatial relations, infer agent interactions, and make safe decisions. However, existing AD datasets and benchmarks mainly target perception, prediction, or planning, and provide limited supervision for reasoning over realistic long-tail driving scenes. We introduce nuReasoning, a large-scale real-world dataset and benchmark for reasoning-centric AD. Following the lineage of nuScenes and nuPlan, nuReasoning advances real-world AD datasets and benchmarks toward reasoning in long-tail driving scenarios. The dataset contains 20,000 clips, each 20 seconds long, collected across multiple cities, with synchronized multi-camera images, LiDAR data, HD maps, object annotations, and human-verified reasoning annotations spanning Spatial Reasoning, Decision Reasoning, and Counterfactual Reasoning. Unlike prior datasets that focus primarily on visual question answering, nuReasoning supports both reasoning evaluation and planning evaluation, enabling a direct study of how reasoning supervision affects driving performance. Experiments show that fine-tuning VLMs on nuReasoning substantially improves driving-specific question answering, while incorporating reasoning supervision into VLA training improves planning performance even when textual reasoning outputs are disabled at inference time. These results establish nuReasoning as a foundation for evaluating and improving robust, interpretable, reasoning-driven AD systems in realistic long-tail settings.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.13274

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs

Rohan Subramanian Thomas, Shikhar Shiromani, Abdullah Chaudhry, Ruizhe Li, Vasu Sharma, Kevin Zhu

原文摘要

Prompt design affects the moral judgments and refusal behavior produced by large language models (LLMs), yet controlled comparisons remain fragmented across datasets and models. We introduce ProMoral-Bench, a benchmark-style comparison of 10 prompting paradigms across four LLM families. Using ETHICS, Scruples, WildJailbreak, and our 200-pair ETHICS-Contrast set, we report task-level metrics together with Moral Competence Score (MCS), jailbreak/over-refusal Safety Robustness Score (SRS), and Unified Moral Safety Score (UMSS). UMSS is a study-specific relative summary of MCS and SRS, not an absolute measure of model safety or moral grounding. In this fixed-template evaluation, compact exemplar-guided scaffolds attain stronger competence-robustness trade-offs at lower token cost than the particular multi-stage variants tested, although multi-stage prompting occasionally improves jailbreak refusal. The few-shot demonstrations are non-overlapping but drawn from the evaluation distributions, so their advantage should not be read as out-of-distribution robustness. Code and data are available at https://github.com/rohanthomas334-sketch/ProMoral_Bench.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.05464

Effective pruning of task-trained recurrent neural networks using noisy fluctuations and connection rescaling

Sanjith Senthil, Rishidev Chaudhuri

原文摘要

Pruning network connections is key to brain function but, despite its importance, there exist few biologically-plausible pruning rules with demonstrated good performance. We evaluate noise-prune, a recently introduced unsupervised local pruning rule for recurrent networks that uses noisy fluctuations to determine the importance of connections. Noise-prune has previously only been empirically tested on random networks without a specific computational function. We show that noise-prune preserves task-performance in task-trained recurrent neural networks, greatly outperforming a strategy that only uses connection magnitude and exceeding a non-local strategy that uses second-order information. Rather than deterministically removing connections that fall below a threshold, noise-prune samples connections to preserve based on their importance and strengthens retained connections to preserve average strength. We show that this sampling and rescaling is essential to good performance, and can augment other pruning strategies. We also find that the optimal empirical degree of rescaling is lower than predicted by the original theoretical argument, and thus develop a new version of noise-prune that outperforms the previous version. Our results demonstrate that a biologically-motivated pruning strategy based on local activity statistics can effectively preserve task performance in functional recurrent networks by combining activity-dependent connection selection with compensatory strengthening of surviving connections.

q-bio.NC · cs.LG · cs.NE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.12289

The Standard Interpretable Model: Design interpretable machine learning methods from elementary symmetries

Pietro Barbiero, Giovanni De Felice, Mateo Espinosa Zarlenga, Francesco Giannini, Filippo Bonchi, Mateja Jamnik, Giuseppe Marra, Ruggero Noris

原文摘要

As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations. However, interpretability lacks general theories to deductively design interpretable methods. This gap between theories and methods results in a fragmented literature and inconsistent evaluation protocols. To fill this gap, we introduce the Standard Interpretable Model (SIM), a general theory that enables the deductive design of interpretable methods from first principles. Specifically, the SIM summarises, in a set of premises, what interpretability is for a target entity. From these premises, the SIM systematically derives interpretability symmetries and corresponding constraints. One can then build interpretable models by either introducing constraints in the optimisation problem or by compiling constraints into an interpretable architecture. The most important finding, both theoretical and empirical, is that full expressivity and interpretability symmetries can coexist in the same model, showing that the trade-off between accuracy and interpretability is an artefact of model design. We demonstrate this on language models (LMs), where SIM-based LMs match the performance of equivalent opaque LMs without making any compromise on interpretability. Beyond this, the SIM shows how to improve the interpretability of existing pre-trained models, highlights underexplored research directions, and unifies a discipline that has long been fragmented, offering pedagogical grounding for interpretability curricula.

cs.LG · cs.AI · cs.NE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.31145

SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference

Amirhossein Abaskohi, Giuseppe Carenini, Peter West, Yuhang He

原文摘要

Large language models increasingly operate over long contexts, where the KV cache grows linearly with sequence length and dominates memory during decoding. Token eviction discards entries permanently, and semantic compression fixes each unit's resolution at prefill, so detail that becomes relevant later cannot be recovered. We propose SeKV, a resolution-adaptive KV cache built around a trained zoom-in mechanism that decides at decode time which compressed spans to restore to token resolution. SeKV segments the context at high-surprisal positions, keeps anchor tokens and span summaries on GPU, and offloads low-rank factors of each span's keys and values to CPU. Lightweight per-head routers select query-relevant spans, which are reconstructed with a learned per-span rank. The cache is lossy but non-evicting: every span stays in attention, coarse or reconstructed. The base LLM stays frozen, and the router adds under 0.1% parameters. Across five backbones and four benchmarks at a 10% GPU-resident KV budget, SeKV outperforms every method that fixes resolution at prefill, improving over the strongest semantic baseline by 2.9 points (5.5% relative). It matches exact-recall offloading caches on LongBench and InfiniteBench and trails on synthetic exact retrieval, while transferring 3 times less data per decoding step than ShadowKV and using the least total memory among the methods we profile. At 128K context, it halves peak GPU memory and cuts total memory by one third relative to full KV caching.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.24584

LAPLEX: The FFT of Learnable Laplace Kernels

Łukasz Struski, Hanna Blazhko, Piotr Kubaty, Jacek Tabor

原文摘要

Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geometry paid for by dense parameters, random features, or low-rank surrogates. To move beyond this trade-off, we introduce LAPLEX, a class of exact, trainable (phased) Laplace-kernel operators. A LAPLEX layer is a typically full-rank dense matrix, implicitly defined by learnable coordinate anchors, with FFT-like scaling. Consequently, it supports trainable matrix--vector operations at vector dimensions up to $10^9$ on modern GPUs. As a neural layer, it yields compact projections and classification heads interpretable as soft, trainable routing models. The same primitive also serves as an efficient Gram operator, enabling high-dimensional covariance models on flattened images of dimension $3 \cdot 10^6$ that preserve visible spatial structure without imposing convolutional bias. These applications reflect a single principle: dense geometry can be learned without storing a dense matrix, which enables data-adaptive global interactions in regimes where ordinary dense layers are out of reach. In this sense, LAPLEX separates expressivity from storage cost: it behaves like a dense trainable matrix, but is represented and applied through a small structured set of parameters.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.15259

Stability and Generalization in Looped Transformers

Asher Labovich

原文摘要

Looped transformers promise test-time compute scaling by spending more iterations on harder problems, but it remains unclear which architectural choices let them extrapolate to harder problems at test time rather than memorize training-specific solutions. We introduce a fixed-point based framework for analyzing looped architectures along three axes of stability -- local attractivity, input-dependence, and geometry -- and use it to characterize when fixed-point iteration yields meaningful predictions. Theoretically, we prove that looped networks without recall have countable fixed points and cannot achieve strong input-dependence at any spectral regime, while recall with outer normalization reliably produces a regime in which fixed points are simultaneously locally-attractive, locally smooth in the input, and supported by stable backpropagation. Empirically, we train small looped transformers on chess, sudoku, and prefix-sums and find that downstream performance tracks the framework's predictions across tasks and architectural configurations. We additionally introduce internal recall, a novel recall placement variant allowing an identity residual path, and exploit its contrasting fixed-point behavior to test our framework's predictions in a controlled setting.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.04998

Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation

Jinju Lee

原文摘要

This paper treats chord progression generation as a standalone task and asks how much old-domain data must be retained in fine-tuning to acquire a new genre without forgetting the old. I study jazz fine-tuning of a pop-pretrained 25M-parameter Music Transformer (84.21% top-1 next-token accuracy on a held-out pop test set). The jazz corpus is over two orders of magnitude smaller than the pop corpus, so every run uses all 1,513 jazz training sequences, and the swept variable is the volume of pop "rehearsal" data mixed alongside: 0, 1K, 2.5K, 5K, or 10K. At the tabulated best epochs every fine-tuned run gains 7 to 9 points of jazz top-1 (the released F1 checkpoint equals the Phase 0 baseline, as the paper's Correction explains), and pop top-1 falls by 2.11 points under jazz-only fine-tuning but by at most 1.19 with rehearsal. Top-1 also scores the three header tokens of each sequence, and two of them shift whole runs: the jazz-majority runs predict the jazz genre marker even for pop songs, and most test songs carry a placeholder C-major key that a checkpoint predicts for every such song or for none, as the best epochs of F1 and F3 happen to do. Scored without the header tokens, every run gains 7.2 to 7.8 jazz points, jazz-only fine-tuning loses 1.48 pop points, and the four rehearsal volumes lose pop at nearly one rate, within 0.11 points of each other at every epoch and 0.73 to 0.90 points below baseline by their last epoch. The smallest volume tested (0.66x the jazz volume) already gives nearly all the measured protection, and no volume stops a slow decline. In informal listening the author more often selects the 10K and 1K endpoints, which carry more committed stylistic identities, than the middle of the sweep, but no formal listening study has been conducted. All six checkpoints and the selection-corrected F1 retrain ft-pop80-v2 are released at https://huggingface.co/PearlLeeStudio.

cs.SD · cs.IR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07176

VINO: Revisiting 3D Representation Learning with Volume Transformers

Adrian Kruse, Kadir Yilmaz, Daan de Geus, Francis Engelmann, Bastian Leibe

原文摘要

Self-supervised learning has given rise to vision foundation models that learn general-purpose image representations transferable across downstream tasks, yet representation learning for 3D scenes has not achieved comparable success. Motivated by this, we identify key limitations of current 3D representation learning approaches and revisit their core design choices. We first replace the commonly used hierarchical PTv3 backbone with the Volume Transformer, a ViT-like architecture for 3D scenes. We then redesign two core objectives of modern approaches built around student-teacher networks: matching representations across views and predicting masked content from visible context. For the first objective, we separate the roles of teacher and student: the teacher provides clean, consistent targets while the student learns invariance to stronger perturbations. For the second objective, we prevent the student from accessing the masked geometry and instead require it to infer missing representations from visible context only. Finally, we redesign 2D-to-3D knowledge distillation, replacing direct regression of view-dependent image features with view-consistent supervision. Together, these changes form VINO, a framework that learns semantic representations of 3D scenes without labels. VINO substantially improves dense linear probing across indoor and outdoor benchmarks and transfers strongly to out-of-domain settings.

cs.CV

查看论文
arXiv ↗PDF ↗