论文检索

Deep Learning · Large Language Models

Ziyan Liu, Xueda Shen, Yuzhe Gu, songyang gao, Kuikun Liu, Cheng, Chengqi Lyu, Dahua Lin, Wenwei Zhang, Kai Chen

Large Reasoning Models (LRMs) have achieved remarkable progress thanks to Reinforcement Learning with Verifiable Rewards (RLVR) on Chain-of-Thoughts (CoTs). However, since long CoTs naturally contain trial and errors and mainstream RLVR approaches choose outcome-correct CoT trajectories for memorization, the redundant explorations in long CoTs are inevitably reinforced through RLVR, which results in the over-thinking issues of LRMs. Previous attempts to resolve the overthinking issue of LRMs mainly give more advantage to shorter trajectories, yet their learning signals are still outcome-based and cannot reduce the memorization of redundant explorations in long CoTs. Therefore, we propose ThoughtFold, a framework that leverages fine-grained preference learning to mitigate redundant explorations for efficient reasoning. ThoughtFold employs an introspective strategy to identify redundancy within each correct trajectory, which yields a spectrum of candidate sub-trajectories. Leveraging this spectrum, we introduce a masked preference optimization objective that explicitly penalizes redundant explorations and encourages the model to directly bridge essential reasoning segments, effectively folding its reasoning chains into a more concise path. Extensive experiments show that ThoughtFold significantly enhances efficiency. It reduces the token usage of DeepSeek-R1-Distill-Qwen-7B by approximately 56\% while maintaining state-of-the-art accuracy.

Theory · Everything Else

YuQing Xie, Ameya Daigavane, Mit Kotak, Tess Smidt

$E(3)$-equivariant neural networks have proven to be extremely effective in a wide range of 3D modeling tasks. A fundamental operation of such networks is the tensor product, which allows interaction between different feature types. Because this operation scales poorly, there has been considerable work towards accelerating this interaction. However, recently \citet{xieprice} have pointed out that most speedups come from a reduction in expressivity rather than true algorithmic improvements on computing Clebsch-Gordan tensor products. A modification of Gaunt tensor product \citep{gaunt} can give a true asymptotic speedup but is incomplete and misses many interactions. In this work, we provide the first complete algorithm which truly provides asymptotic benefits Clebsch-Gordan tensor products. For full CGTP, our algorithm brings runtime complexity from the naive $O(L^6)$ to $O(L^4\log^2 L)$, close to the lower bound of $O(L^4)$. We first show how generalizing fast Fourier based convolution naturally leads to the previously proposed Gaunt tensor product \citep{gaunt}. To remedy antisymmetry issues, we generalize from scalar signals to irrep valued signals, giving us tensor spherical harmonics. We prove a generalized Gaunt formula for the tensor harmonics. Finally, we show that we only need up to vector valued signals to recover the missing interactions of Gaunt tensor product.

Jinxin Yu, Xueqing Chen, Yudong Pan, Lian Liu, shengwen Liang, Huawei Li, Xiaowei Li, ying wang

Instruction-based image editing (IIE) is a vital tool for iterative content creation, enabling multi-round interactions that refine visual details while preserving cross-round consistency. However, this workflow is constrained by the compute-bound nature of Diffusion Transformers (DiTs): because DiTs process tokens uniformly, they waste substantial computation on regions untouched by the instruction. We investigate the Round--Step--Layer hierarchy of DiT-based editing and identify a phenomenon we term Delayed Latent Emergence (DLE). Although pronounced latent changes emerge only in the late denoising stages, deep-layer activations within transformer blocks at the very first sampling step already diverge markedly in edited regions. Building on this insight, we propose CacheEdit, a training-free framework centered on an Adaptive Activation Cache (Acache) that exploits early-step sensitivity to detect invariant tokens and reuse their cached activations across subsequent sampling steps, thereby bypassing redundant computation. Experiments on FLUX.1 Kontext and Qwen-Image-Edit show that CacheEdit achieves up to $2.5\times$ end-to-end acceleration. Moreover, by isolating and reusing static features, CacheEdit mitigates stochastic drift and improves instruction-following and structural consistency over full-recomputation baselines.

Deep Learning · Large Language Models

Xinyu Li, ronghui mu, Lin Li, Tianjin Huang, Gaojie Jin

Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applications. Yet an overlooked threat is Reasoning-Level Denial-of-Service (R-DoS), in which an attacker preserves task correctness but degrades availability by inflating an agent’s reasoning depth or tool-use budget. We introduce OTora, the first unified, two-stage red-teaming framework for instantiating R-DoS attacks. Stage I optimizes an adversarial trigger that induces targeted tool invocations using insertion-aware scoring and dynamic target co-evolution, supporting both black-box and white-box settings. Stage II generates agent-aware reasoning payloads via an ICL-guided genetic search that amplifies overthinking while maintaining correct task outcomes. Across WebShop, Email, and OS agents built on multiple backbone models such as LLaMA-70B and GPT-OSS-120B, OTora achieves up to 10× increases in reasoning tokens and order-of-magnitude latency slowdowns, all while preserving near-baseline task accuracy. Finally, we discuss mitigation strategies for detecting and constraining abnormal reasoning and latency spikes.

Social Aspects · Accountability, Transparency, and Interpretability

Xiao Tian, Jue Fan, Rachael Hwee Ling Sim, Zixuan Wang, Nancy Chen, Bryan Kian Hsiang Low

Data selection studies the problem of identifying high-quality subsets of training data. While some existing works have considered selecting the subset of data with top-$m$ Data Shapley or other semivalues as they account for the interaction among every subset of data, other works argue that Data Shapley can sometimes perform ineffectively in practice and select subsets that are *no better than random*. This raises the questions: **(I)** *Are there certain "Shapley-informative" settings where Data Shapley consistently works well?* **(II)** *Can we strategically utilize these settings to select high-quality subsets consistently and efficiently?* In this paper, we propose a novel data selection framework, **NASH** (Non-linear Aggregation of SHapley-informative components), which **(I)** decomposes the target utility function (e.g., validation accuracy) into simpler, Shapley-informative component functions, and selects data by optimizing an objective that **(II)** aggregates these components non-linearly. We demonstrate that NASH substantially boosts the effectiveness of Shapley/semivalue-based data selection with minimal additional runtime cost.

General Machine Learning · Everything Else

Andong Wang, Yuning Qiu, Haonan Huang, Zhong Jin, Guoxu Zhou, Qibin Zhao

The Tensor Nuclear Norm (TNN), derived from the tensor singular value decomposition, is a widely used low-rank modeling tool that enforces element-wise sparsity on frequency-domain singular values. However, as a direct extension of the matrix nuclear norm, TNN fundamentally assumes single-level spectral sparsity, which is misaligned with the multi-level spectral structures prevalent in real-world data, where low-rankness within frequency components coexists with sparsity across them. To overcome this limitation, we propose the tensor $\ell_p$-Schatten-$q$ quasi-norm ($p,q\in(0,1]$), which enables explicit control of dual spectral sparsity by jointly regularizing inter-frequency sparsity and intra-frequency low-rankness. This formulation strictly generalizes TNN and subsumes several existing tensor regularizers by coupling global frequency sparsity with local spectral low-rankness, leading to a fundamentally different modeling principle. We establish the first minimax error bounds under this model and develop an efficient reweighted optimization algorithm for the resulting nonconvex problem. Numerical experiments on noisy and Poisson tensor completion as well as image clustering demonstrate the effectiveness and robustness of our method across reconstruction and representation learning tasks involving complex multi-way data.

Social Aspects · Accountability, Transparency, and Interpretability

Christodoulos Kechris, Jonathan Dan, David Atienza

Traditional saliency map methods, popularized in computer vision, highlight individual points (pixels) of the input that contribute the most to the model's output. However, in time series, they offer limited insights, as semantically meaningful features are often found in other domains. We introduce Cross-domain Integrated Gradients, a generalization of Integrated Gradients. Our method enables feature attributions in any domain that can be formulated as an invertible, differentiable transformation of the time domain. Crucially, our derivation extends the original Integrated Gradients into the complex domain, enabling frequency-based attributions. We provide the necessary theoretical guarantees, namely, path independence and completeness. We validate our method via controlled experiments with mechanistic analysis, quantitative faithfulness tests, and real-world case studies. Our approach reveals interpretable, problem-specific attributions that time-domain methods cannot capture in three real-world tasks across a variety of model architectures, machine-learning tasks, and cross-domain transforms: frequency-based attribution for a regression task in wearable heart rate extraction, independent component analysis in a classification task for electroencephalography-based seizure detection, and seasonal-trend decomposition for a forecasting problem with a zero-shot time-series foundation model. We release an open-source TensorFlow/PyTorch library to enable plug-and-play cross-domain explainability for time-series models. These results demonstrate the ability of Cross-Domain Integrated Gradients to provide semantically meaningful insights into time-series models that are impossible to achieve with traditional saliency in the time domain.

Social Aspects · Safety

Chenghua Guo, Sihong Xie, Xi Zhang

Reliable uncertainty quantification (UQ) is crucial for deploying graph neural networks (GNNs) in safety-critical settings, yet dominant solutions either rely on costly multi-pass sampling or require retraining—often using *black-box auxiliary* models—to obtain evidential semantics. We propose **X-EviProbe**, a simple and parameter-free *post-hoc* framework that turns a *frozen* GNN into an evidential predictor with a decomposable view of epistemic vs. aleatoric uncertainty. X-EviProbe constructs class-wise Dirichlet evidence by probing the frozen latent space and the model’s native outputs, and incorporates graph structure via lightweight evidence-strength propagation. This yields a transparent evidential representation without retraining or additional neural components. Extensive experiments on seven benchmarks show that X-EviProbe consistently ranks among the top methods for both OOD detection and misclassification detection, improving AUROC by up to **33.4%** and **8.7%** over the strongest baselines.

Probabilistic Methods · Bayesian Models and Methods

Pierre-Louis Ruhlmann, Michael Arbel, Florence Forbes, Pedro Luiz Coelho Rodrigues

Simulation-based inference (SBI) is transforming experimental sciences by enabling parameter estimation in complex non-linear models from simulated data. A persistent challenge, however, is model misspecification: simulators are only approximations of reality, and mismatches between simulated and real data can yield biased or overconfident posteriors. We address this issue by introducing Flow Matching Corrected Posterior Estimation (FMCPE), a framework that leverages the flow matching paradigm to refine simulation-trained posterior estimators using a small set of calibration samples. Our approach proceeds in two stages: first, a posterior approximator is trained on abundant simulated data; second, flow matching transports its predictions toward the true posterior supported by real observations, without requiring explicit knowledge of the misspecification. This design enables FMCPE to combine the scalability of SBI with robustness to distributional shift. Across synthetic benchmarks and real-world datasets, we show that our proposal consistently mitigates the effects of misspecification, delivering improved inference accuracy and uncertainty calibration compared to standard SBI baselines, while remaining computationally efficient.

Deep Learning · Large Language Models

Wei-Lin Chen, Liqian Peng, Tian Tan, Chao Zhao, Jianhang Chen, Ziqian Lin, Alec Go, Yu Meng

Large language models (LLMs) have demonstrated impressive reasoning capabilities by scaling test-time compute via long Chain-of-Thought (CoT). However, recent findings suggest that raw token counts are unreliable proxies for reasoning quality: increased generation length does not consistently correlate with accuracy and may instead signal ``overthinking,'' leading to performance degradation. In this work, we quantify inference-time effort by identifying \emph{deep-thinking tokens}---tokens where internal predictions undergo significant revisions in deeper model layers prior to convergence. Across four challenging mathematical and scientific benchmarks (AIME 24/25, HMMT 25, and GPQA-diamond) and a diverse set of reasoning-focused models (GPT-OSS, DeepSeek-R1, and Qwen3), we show that \textit{deep-thinking ratio} (the proportion of deep-thinking tokens in a generated sequence) exhibits a robust and consistently positive correlation with accuracy, substantially outperforming both length-based and confidence-based baselines. Leveraging this insight, we introduce Think@$n$, a test-time scaling strategy that prioritizes samples with high deep-thinking ratios. We demonstrate that Think@$n$ matches or exceeds standard self-consistency performance while significantly reducing inference costs by enabling the early rejection of unpromising generations based on short prefixes.

Probabilistic Methods · Monte Carlo and Sampling Methods

Yu Wang, Jie Ding, Jonathan Huggins

Tuning stochastic gradient methods such as stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD) for approximate sampling and uncertainty quantification remains challenging, particularly in relevant settings using a large batch size or when the model is misspecified. Existing theory that provides tuning guidance relies on continuous-time limits or strong statistical assumptions, which can become quantitatively inaccurate in these regimes. We address these shortcomings by proposing a new discrete-time approximations to SG(L)D with and without momentum, which enables accurate predictions of the stationary covariance, iterate average covariance, and integrated autocorrelation time. Moreover, we prove quantitative, non-asymptotic error bounds showing that these estimates are sufficiently accurate for practical tuning and uncertainty quantification. Numerical experiments demonstrate that our theory yields improved tuning guidance across a range of models and data-generating distributions where existing approaches fail, including when using the $\beta$-divergence rather than log-loss to obtain statistically robust inferences.

Probabilistic Methods · Everything Else

Qi Kuang, Bowen Gang, Yin Xia

We propose a unified framework to enhance the power of online multiple hypothesis testing procedures based on $e$-values. While $e$-value-based methods offer robust online False Discovery Rate (FDR) control under minimal assumptions, they often suffer from power loss by discarding evidence that exceeds the rejection threshold. We address this inefficiency via the **S**equential **C**ontrol with **O**vershoot **R**efund for **E**-values (SCORE) framework, which leverages the inequality $\mathbb{I}(y \ge 1) \le y - (y-1)_+$ to reclaim this otherwise ``wasted'' evidence. This simple yet powerful insight yields a unified principle for improving a broad class of online testing algorithms. Building on this framework, we develop SCORE-enhanced versions of several state-of-the-art procedures, including SCORE-LOND, SCORE-LORD, and SCORE-SAFFRON, all of which strictly dominate their original counterparts while preserving valid finite-sample FDR control. Furthermore, under mild assumptions, SCORE permits retroactive updates of alpha‑wealth by using the latest decision twice: first to determine its reward or loss, and then to refresh past wealth. Such a mechanism enables more aggressive testing strategies while maintaining valid FDR control, thereby further improving statistical power. The effectiveness of the proposed methods is validated through extensive simulation and real-data experiments.

General Machine Learning · Evaluation

Zuhao zhang, Chengyue Yu, Yuante Li, Chenyi Zhuang, Linjian Mo, Shuai Li

With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynamic, interactive HTML-based applications, which we term **MiniApps**. These applications require models to not only render visual interfaces but also construct customized interaction logic that adheres to real-world principles. However, existing benchmarks primarily focus on algorithmic correctness or static layout reconstruction, failing to capture the capabilities required for this new paradigm. To address this gap, we introduce **MiniAppBench**, the first comprehensive benchmark designed to evaluate principle-driven, interactive application generation. Sourced from a real-world application with **10M+** generations, MiniAppBench distills 500 tasks across six domains (e.g., Games, Science, and Tools). Furthermore, to tackle the challenge of evaluating open-ended interactions where no single ground truth exists, we propose **MiniAppEval**, an agentic evaluation framework. Leveraging browser automation, it performs human-like exploratory testing to systematically assess applications across three dimensions: Intention, Static, and Dynamic. Our experiments reveal that current LLMs still face significant challenges in generating high-quality MiniApps, while MiniAppEval demonstrates high alignment with human judgment, establishing a reliable standard for future research. Our code is available in https://anonymous.4open.science/r/MiniAppBench.

Probabilistic Methods · Everything Else

Zhichao Chen, Zhan Zhuang, Yunfei Teng, Eric Wang, Fangyikang Wang, Zhengnan Li, Tianqiao Liu, Haoxuan Li, Zhouchen Lin

Gradual Domain Adaption (GDA) aims to mitigate domain shift by progressively adapting models from the source domain to the target domain via intermediate domains. However, real intermediate domains are often unavailable or ineffective, necessitating the synthesis of intermediate samples. Flow-based models are recently used for this purpose by interpolating between source and target distributions, but their training typically resorts to sample-based log-likelihood estimation, which can discard useful information and thus degrade GDA performance. The key to addressing this limitation is constructing the intermediate domains via samples directly. To this end, we propose an $\underline{\text{E}}$ntropy-regularized $\underline{\text{S}}$emi-dual $\underline{\text{U}}$nbalanced $\underline{\text{O}}$ptimal $\underline{\text{T}}$ransport (E-SUOT) framework to construct intermediate domains. Specifically, we reformulate flow-based GDA as a Lagrangian dual problem and derive an equivalent objective that circumvents the needs for likelihood estimation. However, the dual problem results in the unstable min–max training procedure. To alleviate this issue, we further introduce entropy regularization to convert it into a more stable alternative optimization procedure. Based on this, we propose a novel GDA training framework and provide theoretical analysis in terms of stability and generalization. Finally, extensive experiments are conducted to demonstrate the efficacy of the E-SUOT framework.

Theory · Probabilistic Methods

Haoxin Sun, Zhongzhi Zhang

The forest matrix of a signed graph plays an important role in network science and social opinion dynamics, yet existing algorithms are mainly designed for unsigned graphs and are difficult to extend to signed graphs. In this paper, we study the problem of efficiently estimating the forest matrix of signed graphs with \(n\) nodes and introduce the signed forest matrix theorem, which establishes the relationship between generalized spanning converging forests and the forest matrix. Based on this result, we propose a novel algorithm GSCF, built on a variant of loop-erased random walks, to generate generalized spanning converging forests in expected \(O(n)\) time. We further develop two sampling algorithms, FMDE and FMDE+, for estimating the diagonal of the forest matrix, both with time complexity \(O(ln)\), where \(l\) is the number of samples. Extensive experiments on various signed graphs show that our methods achieve high estimation accuracy, significantly improve computational efficiency, and scale to graphs with over twenty million nodes. Our source code is publicly available on \url{https://anonymous.4open.science/r/SignedForestDiagonal-FA09}.

Deep Learning · Everything Else

Su Hyeong Lee, Risi Kondor, Richard Ngo

We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log score, and compositions are defined through weighted logarithmic pooling that strictly improves every member's welfare. We prove that strict unanimity is impossible under linear pooling or in binary outcome spaces, but possible with three or more outcomes. Our framework admits recursive structure via cloning invariance, continuity, and openness, while tilt-based analysis rules out trivial duplication. Finally, we formalize an agentic alignment phenomenon in LLMs using our theory: eliciting a benevolent persona ("Luigi'') induces an antagonistic counterpart ("Waluigi''), while a manifest-then-suppress Waluigi strategy yields strictly larger first-order misalignment reduction than pure Luigi reinforcement alone. These results clarify how developing a principled mathematical framework for how subagents can coalesce into coherent higher-level entities provides novel implications for alignment in agentic AI systems.

Deep Learning · Large Language Models

Minki Kang, Wei-Ning Chen, Dongge Han, Huseyin Inan, Lukas Wutschitz, Yanzhi Chen, Robert A Sim, Saravanakumar Rajmohan

Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environments, where success depends on maintaining precise records of actions and observations. However, the resulting unbounded context growth in long-horizon agentic tasks makes two critical bottlenecks: prohibitive inference memory costs and reasoning degradation due to irrelevant information. Existing compression methods fail to fully address this, often relying on brittle heuristics or requiring parameter updates impractical for proprietary or large-scale LLMs. We introduce Agent Context Optimization (ACON), a unified framework that optimally compresses both observations and history into concise, informative representations. Distinct from prior works, ACON employs an optimization in natural language space: it iteratively refines compression guidelines based on failure analysis of the agent, ensuring critical state information is preserved without model fine-tuning. To further minimize computational overhead, we distill the optimized compressor into smaller models. Experiments on AppWorld, OfficeBench, and Multi-objective QA demonstrate that ACON reduces peak token usage by 26–54% while maintaining task performance. Notably, it enables smaller LMs to function effectively as long-horizon agents, achieving up to 46% performance improvement by mitigating context distraction.

Social Aspects · Robustness

Jayoung Kim, Kookjin Lee, Noseong Park, Sanghyun Hong

Implicit neural representations (INRs) encode data as continuous coordinate-based functions parameterized by neural networks, shifting downstream tasks such as image recognition to operate on functional rather than discrete representations. Despite their increasing adoption, the adversarial robustness of INR-based classification pipelines remain largely underexplored. In this work, we present the first systematic study of adversarial robustness in INR-based classifiers. A key challenge is that generating an INR requires $\text{\emph{training}}$ a neural network for each input sample, resulting in an optimization-in-the-loop forward pass that renders standard gradient-based attacks computationally prohibitive. To address this, we design surrogate models that amortizes the INR-generation process, serving as a practical proxy for attacking INR-based classifiers. We also develop speed-up techniques that substantially reduce the training cost of the surrogate. We show that in contrast to recent work, INR-based classifiers are vulnerable: under adversarial input perturbations, classification accuracy collapses to near zero. Moreover, existing countermeasures designed to operate on discrete representations offer limited protection.

Reinforcement Learning · Batch/Offline

Nan Qiao, Sheng Yue, Shuning Wang, Ju Ren

Offline reinforcement learning (RL) can fail spectacularly when bootstrapped temporal-difference (TD) updates amplify their own errors, driving the critic toward extreme and unusable Q-values. A key counterintuitive insight of this work is that collapse is not only a property of the backup rule or network architecture: the optimizer alone can directly trigger or suppress instability. From a control-theoretic viewpoint, we model offline TD learning as a feedback system and analyze Adam-based critic updates. This yields a necessary and sufficient condition for stability: training is stable if and only if the spectral radius of the update dynamics is strictly below one. Further analysis reveals that standard Adam updates can inadvertently distort the parameter geometry, necessitating explicit orthogonality constraints to prevent TD error amplification. To this end, we propose AdamO, an Adam-based optimizer with a decoupled orthogonality correction regulated by a strict task-alignment budget. We prove that this design theoretically guarantees worst-case task safety and preserves Adam’s continuous-time dissipative dynamics. Empirically, AdamO is plug-and-play across diverse offline RL baselines, improving stability and returns across a broad suite of benchmarks.

Social Aspects · Accountability, Transparency, and Interpretability

Elias Shaheen, Avi Mendelson

The general-purpose nature of Large Language Models (LLMs) presents a significant challenge for domain-specific applications, often leading to out-of-domain (OOD) interactions that undermine the provider's intent. Existing methods for detecting such scenarios treat the LLM as an uninterpretable black box and overlook the internal processing of inputs. In this work we show that layer transitions provide a promising avenue for extracting domain-specific signature. Specifically, we present several lightweight ways of learning on internal dynamics encoded using a sparse autoencoder (SAE) that exhibit great capability in distinguishing OOD texts. Building on top of SAEs representation transitions enables us to better interpret the LLM internal evolution of input processing and shed light on its decisions. We provide a comprehensive analysis of the method and benchmark it with the gemma-2 2B and 9B models. Our results emphasize the efficacy of the internal process in capturing fine-grained input-related details.