论文检索

Deep Learning · Large Language Models

Sadegh Mahdavi, Branislav Kisacanin, Shubham Toshniwal, Wei Du, Ivan Moshkov, George Armstrong, Renjie Liao, Christos Thrampoulidis, Igor Gitman

Large language models have achieved remarkable success on final-answer mathematical problems, largely due to the ease of applying reinforcement learning with verifiable rewards. However, the reasoning underlying these solutions is often flawed. Advancing to rigorous proof-based mathematics requires reliable proof verification capabilities. We begin by analyzing multiple evaluation setups and show that focusing on a single benchmark can lead to brittle or misleading conclusions. To address this, we evaluate both proof-based and final-answer reasoning to obtain a more reliable measure of model performance. We then scale two major generative verification methods (GenSelect and LLM-as-a-Judge) to millions of tokens and identify their combination as the most effective framework for solution verification and selection. We further show that the choice of prompt for LLM-as-a-Judge significantly affects the model's performance, but reinforcement learning can reduce this sensitivity. However, despite improving proof-level metrics, reinforcement learning does not enhance final-answer precision, indicating that current models often reward stylistic or procedural correctness rather than mathematical validity. Our results establish practical guidelines for designing and evaluating scalable proof-verification and selection systems.

John Sweeney

Predicting transferability within shared-output model families (e.g., LLMs that share a vocabulary) poses a dilemma: representation-similarity metrics can be uninformative without assumptions about error geometry, while update-geometry metrics are computationally prohibitive. We show that, in a shared-output head setting, representation metrics (e.g., CKA) are non-identifiable for transfer; models can share identical representations yet have orthogonal head updates, so CKA alone cannot reliably rank transfer. We make head Fisher alignment tractable at vocabulary scale ($K{=}128{,}256$) using FisherSketch, a streaming algorithm that compresses joint (activation, error) geometry to a 16KB task signature ($m{=}4096$) with a 192KB per-task streaming state. Beyond the head, we prove a full-network decomposition and bounds, and we propose measurable diagnostics (profile cosine and off-diagonal discrepancy). We validate these on ViT-B/16 and LLMs up to 70B, showing that head/block approximations track the full Fisher and that FisherSketch remains informative in fixed-prefix verbalizer-shift settings where activation similarity cannot distinguish tasks.

Deep Learning · Large Language Models

Aymane El Gadarri, Ali Aouad, Vivek Farias

Traditional large language model (LLM) alignment methods are based on Reinforcement Learning From Human Feedback (RLHF), which learns a single reward model (implicitly or explicitly) from pairwise comparison data. This approach implicitly assumes homogeneous preferences across human labelers---an assumption that is violated in practice. As a result, the learned reward model in RLHF is generally misspecified: Prior work shows that it is inconsistent with the population-average utility, incurring large distortion, and that recovering this utilitarian objective is provably impossible in the worst case. In this work, we show that the average utility is recoverable under a mild assumption. Our method, the Sign Estimator, simply replaces the standard cross-entropy loss function with a notion of binary classification loss and yields a reward model that is ordinally consistent with the population-average utility. We further establish a fast finite-sample convergence rate of $O({n^{-{1}/{3}}})$ , which provides, to our knowledge, the first consistent estimator for heterogeneous preferences that does not suffer from the curse of dimensionality.

Deep Learning · Large Language Models

Haoran Zhang, Yafu Li, Zhi Wang, Zhilin Wang, Shunkai Zhang, Xiaoye Qu, Yu Cheng

Large Reasoning Models (LRMs) increasingly rely on reasoning traces with complex internal structures. However, existing work lacks a unified answer to three fundamental questions: (1) what defines high-quality reasoning, (2) how to reliably evaluate long, implicitly structured reasoning traces, and (3) how to use such evaluation signals for reasoning optimization. To address these challenges, we provide a unified perspective. (1) We introduce the ME$^2$ principle to characterize reasoning quality along macro- and micro-level concerning efficiency and effectiveness. (2) Built on this principle, we model reasoning traces as directed acyclic graphs (DAGs) and develop a DAG-based pairwise evaluation method, capturing complex reasoning structures. (3) Based on this method, we construct the TRM-Preference dataset and train a Thinking Reward Model (TRM) to evaluate reasoning quality at scale. Experiments show that thinking rewards serve as an effective optimization signal. At test time, selecting better reasoning leads to better outcomes (up to 19.3\% gain), and during RL training, thinking rewards enhance reasoning and performance (up to 3.9\% gain) across diverse tasks. Code is available in the supplementary material.

Haoyu Zhao, Jiaxi Gu, Haoran Chen, Qingping Zheng, Yeying Jin, Hongyi Yang, JunqiCheng, Yuang Zhang, Zenghui Lu, Huan Yu 等

Precise camera pose control is critical for video diffusion, yet maintaining geometric consistency remains a challenge. Existing methods that directly inject numerical camera parameters into the diffusion backbone often fail to bridge the gap between abstract coordinates and visual content, leading to structural distortions. To address this issue, we propose CameraNoise, a flow-to-noise warping method that encodes camera motion into a temporally coherent stochastic representation. Unlike conventional conditioning, CameraNoise embeds camera poses directly into the noise space. This decouples motion from scene appearance while faithfully preserving trajectory dynamics. Specifically, we introduce a novel Geometry-guided Reprojection Flow and a noise warping algorithm, which jointly preserve the Gaussian prior of diffusion and ensure consistent noise propagation under camera transformations. By integrating CameraNoise into the diffusion process, our framework delivers stable, high-fidelity videos. Extensive experiments demonstrate that our approach significantly outperforms prior methods in both visual quality and trajectory faithfulness.

Social Aspects · Privacy

Runshan Hu, Yukun Dong, Yingying Huangfu, Ruohan Zhao, Yi Xie, Tieyan Li

Securing *Contextual Integrity* (CI) is critical for privacy-preserving Large Language Model (LLM) agent execution. However, existing agents struggle to balance the agility of direct generation against the prohibitive latency of CI-constrained thinking. To address this, we propose *PrivGate*, a framework that selectively invokes explicit reasoning based on internal privacy signals. Our approach is grounded in the discovery of a *Privacy Manifold*, where models linearly encode privacy sensitivity within their residual streams, even during non-compliant generation. Leveraging this structure, *PrivGate* employs *Latent Gating*, a training-free mechanism that triggers explicit reasoning only when high latent risk is detected, thereby optimizing the efficiency-privacy trade-off by minimizing unnecessary compute. On the real-world PrivacyLens benchmark, *PrivGate* achieves an out-of-distribution AUROC of 0.97 in risk identification, confirming the universality of the discovered manifold. End-to-end evaluations show that *PrivGate* achieves a 70% reduction in privacy leakage with less than 5% overhead, offering a practical pathway to reconcile rigorous CI requirements with the performance demands of LLM agents.

Applications · Everything Else

Esteban Real, Mirko Rossini, Connal de Souza, Manav Garg, Moritz Firsching, Quoc Le, Yao Chen, Akhil Verghese, Ekin Dogus Cubuk, David Park

Transcendental functions, such as the exponential, are central to scientific computing, yet they cannot be natively calculated by digital hardware. Instead, computers must approximate these functions by combining basic operations, such as $\{+, -, \times, \div\}$, using methods like Taylor series. These methods were developed over centuries by mathematicians, who focused on approaches that could attain arbitrary accuracy. However, computers can handle most applications by using only finite-precision types, like \emph{float32}, where any accuracy beyond the type's precision is effectively discarded. We explore, therefore, whether forgoing arbitrary accuracy can lead to the discovery of more efficient approximations. The evolutionary method of symbolic regression is particularly suitable, as it can search for arbitrary operation combinations and can optimize non-differentiable objectives, such as the number of operations used. Our results show that evolution can discover computer programs that outperform established methods in this setting, despite having no prior mathematical knowledge beyond the calculation of the basic operations. Starting from empty code, symbolic regression constructs programs representing novel mathematical expressions. In particular, we discovered a 10-operation program that approximates the exponential function to 14 significant figures, exceeding the accuracy of previously known approximations of this size by more than 6 orders of magnitude.

Deep Learning · Everything Else

Bin Hu, Xiancong Pan, Dongjin Yu, Tianyi Hu

Artificial intelligence has achieved remarkable breakthroughs in fields such as text, image, and video analysis, with deep learning serving as the mainstream paradigm widely adopted across applications. Trained deep learning models can be integrated into various applications either through fine-tuning or without any modification. While this practice promotes the advancement of artificial intelligence, it also raises concerns regarding intellectual property protection and information security risks. Therefore, it is necessary to propose relevant methods to measure the similarity between models. Existing code clone detection techniques are insufficient to address this issue. In this paper, we formalize deep learning models as weighted graph objects defined by both computational structure and parameter distribution. Drawing inspiration from code clone analysis, we provide the first definition of model cloning and design a method for model similarity detection. The framework characterizes model topology at the structural level based on normalized computational graphs, and at the weight level, it employs a method that does not require explicit parameter alignment to measure the statistical similarity of weight parameters. Experiments on a synthetic model clone benchmark dataset and real-world open-source models demonstrate that the proposed method can accurately detect similar models. The experimental analysis results align with the expected similarity changes during model fine-tuning and derivation processes. This method provides a unified and extensible quantitative foundation for model lineage analysis, model retrieval, and intellectual property protection of models.

Deep Learning · Generative Models and Autoencoders

David Li, Nikita Gushchin, Dmitry Abulkhanov, Eric Moulines, Ivan Oseledets, Maxim Panov, Aleksandr Korotin

Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique originally developed to accelerate continuous diffusion models, to the discrete setting. Nonetheless, this extension introduces both theoretical and practical challenges. From a theoretical perspective, the inverse distillation objective lacks uniqueness guarantees, which may lead to suboptimal solutions. From a practical standpoint, backpropagation in the discrete space is non-trivial and often unstable. To overcome these challenges, we first provide a theoretical result demonstrating that our inverse formulation admits a unique solution, thereby ensuring valid optimization. We then introduce gradient-stable relaxations to support effective training. As a result, experiments on multiple DLMs show that our method, *Inverse-distilled Diffusion Language Models (IDLM)*, reduces the number of inference steps by $4 \times$-$64 \times$, while preserving the teacher model’s entropy and generative perplexity.

Social Aspects · Security

Qi Zhao, Christian Wressnegger

Recent training-time defenses against neural backdoors isolate a benign subset from poisoned training data, to learn a backdoor-free model from it. In this paper, we formulate this defense strategy as a coreset selection problem, giving rise to so-called “Anti-Backdoor Coreset Selection.” Since poisonous samples have a) lower prediction uncertainty and are b) less frequent than benign samples, coreset selection naturally focuses more on samples associated with benign functionality than the backdoor functionality. We use the Cumulative Entropy as selection criterion to further facilitate this effect. The metric tracks the learning dynamics of training samples and allowing us to select benign samples with high informativeness for the coreset. Additionally, we unlearn the chosen samples in each epoch to facilitate the separability between benign and poisonous samples. Together, this yields an exceptionally effective training-time defense that constructs a benign coreset to train a backdoor-free model. Unlike prior defenses that compromise natural accuracy and fail against certain attacks, our method mitigates backdooring attacks consistently with a negligible impact on natural performance.

Deep Learning · Large Language Models

Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang, Justin Deschenaux, Jingyu Liu, John Thickstun, Ante Jukić

Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by strong perplexity on language modeling benchmarks. In this work, we present the first scaling law study of Uniform-state and interpolating discrete diffusion methods. We also show that masked diffusion models can be made approximately 12% more FLOPs-efficient when trained with a simple cross-entropy objective. We find that perplexity is informative within a diffusion family but can be misleading across families, where models with worse likelihood scaling may be preferable due to faster and more practical sampling, as reflected by the speed-quality Pareto frontier. These results challenge the view that masked diffusion is categorically the future of diffusion language modeling and that perplexity alone suffices for cross-algorithm comparison. Scaling all methods to 1.7B parameters, we show that uniform-state diffusion remains competitive on likelihood-based benchmarks and outperforms autoregressive and masked diffusion models on GSM8K, despite worse validation perplexity. Overall, **our results challenge the view that masked diffusion is categorically the future of diffusion language modeling** and that perplexity alone suffices for cross-algorithm comparison.

General Machine Learning · Transfer, Multitask and Meta-learning

Anushka Tiwari, Kaiyi Ji

While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limits later tasks from improving earlier ones, leaving backward knowledge transfer underexplored. We address this limitation by proposing Selective bAckward refinement for positive Backward knowledge transfER (SABER), a replay-free framework that enables controlled backward transfer in prompt-based continual learning. SABER explicitly determines when backward refinement is beneficial using complementary task-correlation criteria based on prompt-gradient geometry and loss-distribution similarity, and how to perform refinement safely by restricting updates to non-interfering directions in the prompt parameter space. We provide theoretical guarantees showing that SABER’s backward refinements are interference-free and induce non-increasing loss under mild conditions. Extensive experiments across multiple continual learning benchmarks with different task orders, and diverse pretrained backbones, including T5-Large, LLaMA, and Qwen, demonstrate that SABER consistently achieves positive backward transfer while maintaining strong overall average performance.

General Machine Learning · Hardware and Software

Ayan Banerjee, BIN XU, Sandeep Gupta

Continuous-depth neural networks (CDNNs), including Neural Ordinary Differential Equations (ODEs) and liquid-time-constant (LTC) networks, suffer from high computational costs due to solving numerous nonlinear ODEs during training and inference. We introduce Continuous Depth Acceleration (CoDA), a framework that leverages Mori–Zwanzig/Koopman operator theory to replace continuous-depth layers requiring multiple nonlinear ODEs with a compact GRU module, a single low-dimensional linear ODE, and a dense layer. We prove PAC learnability of CoDA, establishing that this transformation preserves accuracy and can be applied repeatedly across multiple layers with unified backpropagation. Experiments on the Liquid Foundation Model (LFM-1.2B) demonstrate $6.7\times$ training speedup and $1.8\times$ inference speedup without loss of accuracy. Across six real-world LTC applications, CoDA consistently outperforms state-of-the-art acceleration techniques—including neural flows, model order reduction, and variational formulations—in both training and inference time while maintaining competitive or superior accuracy.

Deep Learning · Generative Models and Autoencoders

Qijie Zhu, Zeqi Ye, Han Liu, Zhaoran Wang, Minshuo Chen

Adaptation methods have been a workhorse for unlocking the transformative power of pre-trained diffusion models in diverse applications. Existing approaches often abstract adaptation objectives as a reward function and steer diffusion models to generate high-reward samples. However, these approaches can incur high computational overhead due to additional training, or rely on stringent assumptions on the reward such as differentiability. Moreover, despite their empirical success, theoretical justification and guarantees are seldom established. In this paper, we propose $\texttt{DOIT}$ ($\textbf{D}$oob-$\textbf{O}$riented $\textbf{I}$nference-time $\textbf{T}$ransformation), a training-free and computationally efficient adaptation method that applies to generic, non-differentiable rewards. The key framework underlying our method is a measure transport formulation that seeks to transport the pre-trained generative distribution to a high-reward target distribution. We leverage Doob's $h$-transform to realize this transport, which induces a dynamic correction to the diffusion sampling process and enables efficient simulation-based computation without modifying the pre-trained model. Theoretically, we establish a high probability convergence guarantee to the target high-reward distribution via characterizing the approximation error in the dynamic Doob's correction. Empirically, on D4RL offline RL benchmarks, our method consistently outperforms state-of-the-art baselines while preserving sampling efficiency.

Charles Westphal, Keivan Navaie, Fernando Rosas

Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels. Prior work demonstrated this threat but relied on trivially recoverable encodings. We formalize payload recoverability via classifier accuracy and show previous schemes achieve 100\% recoverability. In response, we introduce low-recoverability steganography, replacing arbitrary mappings with embedding-space-derived ones. For Llama-8B (LoRA) and Ministral-8B (LoRA) trained on TrojanStego prompts, exact secret recovery rises from 17$\rightarrow$30\% (+78\%) and 24$\rightarrow$43\% (+80\%) respectively, while on Llama-70B (LoRA) trained on Wiki prompts, it climbs from 9$\rightarrow$19\% (+123\%), all while reducing payload recoverability. We then discuss detection. We argue that detecting fine-tuning-based steganographic attacks requires approaches beyond traditional steganalysis. Standard approaches measure distributional shift, which is an expected side-effect of fine-tuning. Instead, we propose a mechanistic interpretability approach: linear probes trained on later-layer activations detect the secret with up to 33\% higher accuracy in fine-tuned models compared to base models, even for low-recoverability schemes. This suggests that malicious fine-tuning leaves actionable internal signatures amenable to interpretability-based defenses.

General Machine Learning · Supervised Learning

Arda Uzunoglu, Alvin Zhang, Daniel Khashabi

Weak-to-strong generalization studies how to improve a strong student using supervision from a weaker teacher when reliable labels are scarce. We view this primarily as a data selection problem, where the key challenge is to identify which weak labels are reliable enough to serve as a training signal. To address this, we introduce trust functions that assign each weak label a scalar trust score and use these scores to filter weak supervision. Across several domains, including world knowledge, quantitative reasoning, decision making, trust filtering yields students that match and sometimes surpass ground-truth supervision, achieving near-lossless weak-to-strong generalization. Moreover, trust functions enable an iterative weak-to-strong chain that compounds gains by training a student and reusing it as the next teacher, producing the strongest final model. Our analyses suggest that neural trust functions improve learning through more than label error reduction. They induce an implicit easy-first curriculum, recover near-optimal alternatives where ground truth labels are incomplete, and produce more coherent gradient updates, offering a mechanistic account of the stability and efficiency of trust-filtered weak-to-strong generalization.

Deep Learning · Large Language Models

Haoran Zhang, Yafu Li, Zhi Wang, Zhilin Wang, Shunkai Zhang, Xiaoye Qu, Yu Cheng

Large Reasoning Models (LRMs) increasingly rely on reasoning traces with complex internal structures. However, existing work lacks a unified answer to three fundamental questions: (1) what defines high-quality reasoning, (2) how to reliably evaluate long, implicitly structured reasoning traces, and (3) how to use such evaluation signals for reasoning optimization. To address these challenges, we provide a unified perspective. (1) We introduce the ME$^2$ principle to characterize reasoning quality along macro- and micro-level concerning efficiency and effectiveness. (2) Built on this principle, we model reasoning traces as directed acyclic graphs (DAGs) and develop a DAG-based pairwise evaluation method, capturing complex reasoning structures. (3) Based on this method, we construct the TRM-Preference dataset and train a Thinking Reward Model (TRM) to evaluate reasoning quality at scale. Experiments show that thinking rewards serve as an effective optimization signal. At test time, selecting better reasoning leads to better outcomes (up to 19.3\% gain), and during RL training, thinking rewards enhance reasoning and performance (up to 3.9\% gain) across diverse tasks. Code is available in the supplementary material.

Deep Learning · Large Language Models

Matan Levi, Daniel Ohayon, Ariel Blobstein, Ravid Sa, Ian Molloy, Yair Allouche

Large language models (LLMs) are transforming everyday applications, yet they lag behind in specialized fields, such as cybersecurity, due to a lack of high-quality, domain-specific models and training datasets. To address this gap, we present CyberPal 2.0, a family of cybersecurity-expert small language models (SLMs) ranging from 4B–20B parameters. To train CyberPal 2.0, we generate an enriched chain-of-thought cybersecurity instruction dataset built with our data enrichment and formatting pipeline, SecKnowledge 2.0, which integrates expert-in-the-loop steering of reasoning formats alongside LLM-driven multi-step grounding, yielding higher-fidelity, task-grounded reasoning traces for security tasks. Across diverse cybersecurity benchmarks, *CyberPal 2.0 consistently outperforms its baselines and matches or surpasses various open and closed-source frontier models*, while remaining a fraction of their size. On core threat-investigation tasks, such as correlating vulnerabilities and bug tickets with weaknesses, *our best 20B-parameter model outperforms GPT-4o, o1, o3-mini, and Sec-Gemini v1, ranking first, while our smallest 4B-parameter model ranks second. On core cyber threat intelligence knowledge tasks, our models outperform almost all tested frontier models, ranking second only to Sec-Gemini v1*. To foster reproducibility and practical adoption, we will release our models as open source.

Deep Learning · Large Language Models

Haoran Zhang, Yafu Li, Xuyang Hu, Dongrui Liu, Zhilin Wang, Bo Li, Yu Cheng

Large language models (LLMs) are increasingly applied in diverse real-world applications, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These specifications, categorized into safety-spec and behavioral-spec, vary across scenarios and evolve with changing preferences and requirements. We formalize this challenge as specification alignment, focusing on LLMs' ability to follow dynamic, scenario-specific spec from both behavioral and safety perspectives. To address this challenge, we introduce SpecBench, a unified benchmark for measuring specification alignment, covering 5 scenarios, 103 spec, and 1,500 prompts. Experiments on 15 reasoning and 18 instruct models with several Test-Time Deliberation (TTD) methods, including Self-Refine, TPO, and MoreThink, show that SpecBench effectively reveals alignment gaps and that test-time deliberation improves specification alignment. Based on previous TTD methods, we further propose Align3, a lightweight method with hierarchical reflection and revision to reason over specification boundaries, advancing the safety-helpfulness trade-off frontier with minimal overhead. These results highlight test-time deliberation as an effective strategy for reasoning over the real-world specification boundaries. Code and data are available at supplementary material.

Deep Learning · Self-Supervised Learning

Houtan Ghaffari, Lukas Rauch, Christoph Scholz, Paul Devos

Probing is widely adopted in computer vision to faithfully evaluate self-supervised learning (SSL) embeddings, as finetuning may misrepresent their inherent quality. In contrast, audio SSL models still rely on finetuning because simple probing fails to unlock their full potential and alters their rankings when competing for SOTA on AudioSet. Hence, a robust and efficient probing mechanism is required to guide the trajectory of audio SSL towards reliable and reproducible methods. We introduce *Convex Gated Probing* (CGP), a prototype-based method that drastically closes the gap between finetuning and probing in audio. CGP efficiently utilizes all frozen layers via a gating mechanism and exposes the location of latent task-relevant information. Guided by CGP, we rework the entire SSL pipeline to address reproducibility issues in current SOTA audio models that use legacy implementations of prior SSL methods. By refining data preprocessing, model architecture, and pretraining recipe, we introduce *Better Audio Transformer* (BAT), and establish new SOTA on audio benchmarks.