论文检索

Theory · Learning Theory

Kazushi Mimura, Junichi Takeuchi, Yuto Sumikawa, Yoshiyuki Kabashima, Anthony CC Coolen

Dense associative memory, a fundamental instance of modern Hopfield networks, can store a large number of memory patterns as equilibrium states of recurrent networks. While the stationary-state storage capacity has been investigated, its dynamical properties have not yet been discussed. In this paper, we analyze the dynamics using an exact approach based on generating functional analysis. We show results on convergence properties of memory retrieval, such as the convergence time and the size of the attraction basins. Our analysis enables a quantitative evaluation of the convergence time and the storage capacity of dense associative memory, which is useful for model design. Unlike the traditional Hopfield model, the retrieval of a pattern does not act as additional noise to itself, suggesting that the structure of modern networks makes recall more robust. Furthermore, the methodology addressed here can be applied to other energy-based models, and thus has the potential to contribute to the design of future architectures.

Stella Li, Avinandan Bose, Faeze Brahman, Simon Du, Pang Wei Koh, Maryam Fazel, Yulia Tsvetkov

Current large language model (LLM) development treats task-solving and preference-alignment as separate challenges, optimizing first for objective correctness, then for alignment to aggregated human preferences. This paradigm fails in human-facing applications where solving a problem correctly is insufficient if the response mismatches the user’s needs. This challenge intensifies in just-in-time scenarios where no prior user interaction history exists due to cold-start conditions or privacy constraints. LLMs need to proactively identify what they don’t know about the user, strategically elicit preference values through questioning, then adapt their reasoning processes and responses accordingly—a complicated chain of cognitive processes which we term personalized reasoning. We introduce PREFDISCO, an evaluation methodology that transforms static benchmarks into interactive personalization tasks using psychologically-grounded personas with sparse, context-dependent preferences, and define PREFALIGN as a fine-grained rubric-based metric for measuring preference alignment. PREFDISCO builds scenarios where identical questions require different reasoning chains depending on user context, as optimal explanation approaches vary by individual expertise and preferences while maintaining factual accuracy. Evaluation of 21 frontier models across 10 tasks reveals 29.0% of naive personalization attempts produce worse preference alignment than generic responses, yet generic responses also fail to serve individual user needs. These findings suggest personalized reasoning requires dedicated development rather than emerging naturally. PREFDISCO provides a foundation for developing systems that can adapt to individual users in education, healthcare, and technical domains where personalization is critical.

Gabriela Moisescu-Pareja, Gavin McCracken, Harley Wiltzer, Colin Daniels, Vincent Létourneau, Doina Precup, Jonathan Love

The Clock and Pizza interpretations, associated with architectures differing in either uniform or learnable attention, were introduced to argue that different architectural designs can yield distinct circuits for modular addition. In this work, we show that this is not the case, and that both the uniform and trainable attention architectures implement the same algorithm via topologically and geometrically equivalent representations. Our methodology goes beyond the interpretation of individual neurons and weights. Instead, we identify all of the neurons corresponding to each learned representation and then study the collective group of neurons as one entity. This method reveals that each learned representation is a manifold that we can study utilizing tools from topology. Based on this insight, we can statistically analyze the learned representations across hundreds of circuits to demonstrate the similarity between learned modular addition circuits that arise naturally from common deep learning paradigms.

Social Aspects · Accountability, Transparency and Interpretability

Mélissa Tamine, Benjamin Heymann, Maxime Vono, Patrick Loiseau

Semivalue–based data valuation uses cooperative‐game theory intuitions to assign each data point a value reflecting its contribution to a downstream task. Still, those values depend on the practitioner’s choice of utility, raising the question: *How robust is semivalue-based data valuation to changes in the utility?* This issue is critical when the utility is set as a trade‐off between several criteria and when practitioners must select among multiple equally valid utilities. We address this by introducing the notion of a dataset’s *spatial signature*: given a semivalue, we embed each data point into a lower-dimensional space in which any utility becomes a linear functional, making the data valuation framework amenable to a simpler geometric picture. Building on this, we propose a practical methodology centered on an explicit robustness metric that informs practitioners whether and by how much their data valuation results will shift as the utility changes. We validate this approach across diverse datasets and semivalues, demonstrating strong agreement with rank‐correlation analyses and offering analytical insight into how choosing a semivalue can amplify or diminish robustness.

Social Aspects · Trustworthy Machine Learning

Yunseok Han, Yejoon Lee, Jaeyoung Do

Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true decision process, undermining reliability and trust. We introduce a formal framework for *reasoning faithfulness*, defined by two testable conditions: *stance consistency* (a coherent stance linking reasoning to answer) and *causal influence* (the stated reasoning causally drives the answer under output-level interventions), explicitly decoupled from accuracy. To operationalize this, we present **RFEval**, a benchmark of 7,186 instances across seven tasks that probes faithfulness via controlled, output-level counterfactual interventions. Evaluating twelve open-source LRMs, we find unfaithfulness in 49.7% of outputs, predominantly from stance inconsistency. Failures are concentrated in brittle, convergent domains such as math and code, and correlate more with post-training regimes than with scale: within-family ablations indicate that adding current RL-style objectives on top of supervised fine-tuning can *reduce* reasoning faithfulness, even when accuracy is maintained. Crucially, *accuracy is neither a sufficient nor a reliable proxy for faithfulness*: once controlling for model and task, the accuracy–faithfulness link is weak and statistically insignificant. Our work establishes a rigorous methodology for auditing LRM reliability and shows that trustworthy AI requires optimizing not only for correct outcomes but also for the structural integrity of the reasoning process. Our code and dataset can be found at project page: https://aidaslab.github.io/RFEval/

Optimization · Learning for Optimization

Xuanhao Pan, Chenguang Wang, Chaolong Ying, Ye XUE, Tianshu Yu

The ``Heatmap + Monte Carlo Tree Search (MCTS)'' paradigm has recently emerged as a prominent framework for solving the Travelling Salesman Problem (TSP). While considerable effort has been devoted to enhancing heatmap sophistication through advanced learning models, this paper rigorously examines whether this emphasis is justified, critically assessing the relative impact of heatmap complexity versus MCTS configuration. Our extensive empirical analysis across diverse TSP scales, distributions, and benchmarks reveals two pivotal insights: \textbf{1}) The configuration of MCTS strategies significantly influences solution quality, underscoring the importance of meticulous tuning to achieve optimal results and enabling valid comparisons among different heatmap methodologies. \textbf{2}) A rudimentary, parameter-free heatmap based on the intrinsic $k$-nearest neighbor structure of TSP instances, when coupled with an optimally tuned MCTS, can match or surpass the performance of more sophisticated, learned heatmaps, demonstrating robust generalizability on problem scale and distribution shift. To facilitate rigorous and fair evaluations in future research, we introduce a streamlined pipeline for standardized MCTS hyperparameter tuning. Collectively, these findings challenge the prevalent assumption that heatmap complexity is the primary determinant of performance, advocating instead for a balanced integration and comprehensive evaluation of both learning and search components within this paradigm.

Applications · Language, Speech and Dialog

Wenjie Ma, Andrei Cojocaru, Neel Kolhe, Haihan Zhang, Vincent Zhuang, Matei Zaharia, Sewon Min

Recent advances in large language models (LLMs) for mathematical reasoning have largely focused on tasks with easily verifiable final answers while generating and verifying natural language math proofs remains an open challenge. We identify the absence of a reliable, fine-grained evaluator for LLM-generated math proofs as a critical gap. To address this, we propose a systematic methodology for developing and validating evaluators that assign fine-grained scores on a 0-7 scale to model-generated math proofs. To enable this study, we introduce ProofBench, the first expert-annotated dataset of fine-grained proof ratings, spanning 145 problems from six major math competitions (USAMO, IMO, Putnam, etc) and 435 LLM-generated solutions from Gemini-2.5-Pro, o3, and DeepSeek-R1. Using ProofBench as a testbed, we systematically explore the evaluator design space across key axes: the backbone model, input context, instructions and evaluation workflow. Our analysis delivers ProofGrader, an evaluator that combines a strong reasoning backbone LM, rich context from reference solutions and marking schemes, and a simple ensembling method; it achieves a low Mean Absolute Error (MAE) of 0.926 against expert scores, significantly outperforming naive baselines. Finally, we demonstrate its practical utility in a best-of-$n$ selection task: at $n=16$, ProofGrader achieves an average score of 4.14/7, closing 78\% of the gap between a naive binary evaluator (2.48) and the human oracle (4.62), highlighting its potential to advance downstream proof generation.

Deep Learning · Robustness

Louis Chen, Bobbie Chern, Eric Eckstrand, Amogh Mahapatra, Johannes Royset

Labeling errors in datasets are common, arising in a variety of contexts, such as human labeling and weak labeling. Although neural networks (NNs) can tolerate modest amounts of these errors, their performance degrades substantially once the label error rate exceeds a certain threshold. We propose the Rockafellian Relaxation Method (RRM) -- an architecture-independent, loss reweighting approach to enhance the capacity of neural network methods to accommodate noisy labeled data. More precisely, it functions as a wrapper, modifying any methodology's training loss - particularly, the supervised component. Experiments indicate RRM can provide an increase to accuracy across classification tasks in computer vision and natural language processing (sentiment analysis). This observed potential for increase holds irrespective of dataset size, noise generation (synthetic/human), data domain, and adversarial perturbation.

Devvrit Khatri, Lovish Madaan, Rishabh Tiwari, Rachit Bansal, Venkata Sai Surya Subramanyam Duvvuri, Manzil Zaheer, Inderjit Dhillon, David Brandfonbrener, Rishabh Agarwal

Reinforcement learning (RL) has become central to training large language models (LLMs), yet the field lacks predictive scaling methodologies comparable to those established for pre-training. Despite rapidly rising compute budgets, there is no principled understanding of how to evaluate algorithmic improvements for scaling RL compute. We present the first large-scale systematic study, amounting to more than 400,000 GPU-hours, that defines a principled framework for analyzing and predicting RL scaling in LLMs. We fit sigmoidal compute-performance curves for RL training and ablate a wide range of common design choices to analyze their effects on asymptotic performance and compute efficiency. We observe: (1) Not all recipes yield similar asymptotic performance, Details such as loss aggregation, normalization, curriculum, and off-policy algorithm primarily modulate compute efficiency without materially shifting the asymptote, and (3) Stable, scalable recipes follow predictable scaling trajectories, enabling extrapolation from smaller-scale runs. Combining these insights, we propose a _best-practice_ recipe, ScaleRL, and demonstrate its effectiveness by successfully scaling and predicting validation performance on a single RL run scaled up to 100,000 GPU-hours. Our work provides both a _scientific framework_ for analyzing scaling in RL and a practical recipe that brings RL training closer to the predictability long achieved in pre-training.

Qingyuan Tian, Wenhong Zhu, Xiaoran Liu, Xiaofeng Wang, Rui Wang

Rotary Position Embedding (RoPE)-extension refers to modifying or generalizing the Rotary Position Embedding scheme to handle longer sequences than those encountered during pre-training. However, current extension strategies are highly diverse and lack a unified theoretical foundation. In this paper, we propose $\textbf{\textit{MrRoPE (Mixed-radix RoPE)}}$, a generalized encoding formulation based on a radix system conversion perspective, which elegantly unifies various RoPE-extension approaches as distinct radix conversion strategies. Based on this theory, we introduce two training-free extensions, $\textbf{\textit{MrRoPE-Uni}}$ and $\textbf{\textit{MrRoPE-Pro}}$, which leverage uniform and progressive radix conversion strategies, respectively, to achieve “train short, test long” generalization. Without fine-tuning, MrRoPE-Pro sustains over 85% recall in the 128K-context Needle-in-a-Haystack test and achieves more than double YaRN’s accuracy on Infinite-Bench retrieval and dialogue subsets. Theoretical analysis confirms that MrRoPE-Pro effectively raises the upper bound of RoPE's attainable encoding length, which further validates the reliability and utility of our theory and methodology.

Aakash Sunil Lahoti, Kevin Li, Berlin Chen, Caitlin Wang, Aviv Bick, Zico Kolter, Tri Dao, Albert Gu

Scaling inference-time compute has emerged as an important driver of LLM performance, making inference efficiency a central focus of model design alongside model quality. While current Transformer models deliver strong quality, their quadratic compute and linear memory requirements make inference expensive. This has spurred the development of sub-quadratic models with reduced compute and constant memory requirements. However, many recent linear models trade off model quality and capability for algorithmic efficiency, failing on tasks such as state tracking. Moreover, their theoretically linear inference remains hardware-inefficient in practice. Guided by an inference-first perspective, we introduce three core methodological improvements inspired by the state space model (SSM) viewpoint of linear models. We combine: (1) a more expressive recurrence derived from SSM discretization, (2) a complex-valued state update rule enabling richer state tracking, and (3) a multi-input, multi-output (MIMO) formulation that improves model performance without increasing decode latency. Together with architectural refinements, Mamba-3 achieves significant gains across retrieval, state-tracking, and downstream language modeling tasks. At the 1.5B scale, Mamba-3 improves average downstream accuracy by 0.6 percentage points compared to the next best model (Gated DeltaNet), with the MIMO variant further improving accuracy by an additional 1.2 points, for a total gain of 1.8 points. Across state-size experiments, Mamba-3 achieves comparable perplexity to Mamba-2 despite using half the state size. These results demonstrate that Mamba-3 advances the performance–efficiency frontier.

Houyi Li, Ka Man Lo, Shijie Xuyang, Ziqi Wang, Wenzhen Zheng, Haocheng Zhang, Zhao Li, Shuigeng Zhou, Xiangyu Zhang, Daxin Jiang

Mixture-of-Experts (MoE) language models dramatically expand model capacity and achieve remarkable performance without increasing per-token compute. However, can MoEs surpass dense architectures under strictly equal resource constraints — that is, when the total parameter count, training compute, and data budget are identical? This question remains under-explored despite its significant practical value and potential. In this paper, we propose a novel perspective and methodological framework to study this question thoroughly. First, we comprehensively investigate the architecture of MoEs and achieve an optimal model design that maximizes the performance. Based on this, we subsequently find that an MoE model with activation rate in an optimal region is able to outperform its dense counterpart under the same total parameter, training compute and data resource. More importantly, this optimal region remains consistent across different model sizes. Although additional amount of data turns out to be a trade-off for enhanced performance, we show that this can be resolved via reusing data. We validate our findings through extensive experiments, training nearly 200 language models at 2B scale and over 50 at 7B scale, cumulatively processing 50 trillion tokens. All code and models will be released publicly.

Computer Vision · Vision Models & Multimodal

Hongxing Li, Dingming Li, Zixuan Wang, Yuchen Yan, Hang Wu, Wenqi Zhang, Yongliang Shen, Weiming Lu, Jun Xiao, Yueting Zhuang

Spatial reasoning remains a fundamental challenge for Vision-Language Models (VLMs), with current approaches struggling to achieve robust performance despite recent advances. We identify that this limitation stems from a critical gap: existing methods attempt to learn spatial reasoning directly without establishing the hierarchical foundations of perception and understanding. To address this challenge, we present a comprehensive methodology for building spatial intelligence progressively. We introduce SpatialLadder-26k, a multimodal dataset containing 26,610 samples spanning object localization, single-image, multi-view, and video spatial reasoning tasks, constructed through a standardized pipeline that ensures systematic coverage across modalities. Building on this dataset, we design a three-stage progressive training framework that (1) establishes spatial perception through object localization, (2) develops spatial understanding through multi-dimensional spatial tasks, and (3) strengthens complex reasoning via reinforcement learning with verifiable rewards. This approach yields SpatialLadder, a 3B-parameter model that achieves state-of-the-art performance on spatial reasoning benchmarks, with 23.4% average improvement over the base model, surpassing GPT-4o by 20.8% and Gemini-2.0-Flash by 10.1%. Notably, SpatialLadder maintains strong generalization with 7.2% improvement on out-of-domain benchmarks, demonstrating that progressive training from perception to reasoning is essential for robust spatial intelligence.

Deep Learning · Generative Models and Autoencoders

Yuchen Yan, Yongliang Shen, Yang Liu, Jin Jiang, Mengdi Zhang, Jian Shao, Yueting Zhuang

Advanced reasoning in large language models has achieved remarkable performance on challenging tasks, but the prevailing long-context reasoning paradigm faces critical limitations: quadratic computational scaling with sequence length, reasoning constrained by maximum context boundaries, and performance degradation beyond pre-training context windows. Existing approaches primarily compress reasoning chains without addressing the fundamental scaling problem. To overcome these challenges, we introduce InftyThink, a paradigm that transforms monolithic reasoning into an iterative process with intermediate summarization. By interleaving short reasoning segments with concise progress summaries, our approach enables unbounded reasoning depth while maintaining bounded computational costs. This creates a characteristic sawtooth memory pattern that significantly reduces computational complexity compared to traditional approaches. Furthermore, we develop a methodology for reconstructing long-context reasoning datasets into our iterative format, transforming OpenR1-Math into 333K training instances. Experiments across multiple model architectures demonstrate that our approach reduces computational costs while improving performance, with Qwen2.5-Math-7B showing 3-11% improvements across MATH500, AIME24, and GPQA_diamond benchmarks. Our work challenges the assumed trade-off between reasoning depth and computational efficiency, providing a more scalable approach to complex reasoning without architectural modifications.

Theory · Interpretability and Visualization

Jim Maar, Denis Paperno, Callum McDougall, Neel Nanda

Prior work suggests that language models, while trained on next token prediction, show implicit planning behavior: they may select the next token in preparation to a predicted future token, such as a likely rhyming word, as supported by a prior qualitative study of Claude 3.5 Haiku using a cross-layer transcoder. We propose much simpler techniques for assessing implicit planning in language models. With case studies on rhyme poetry generation and question answering, we demonstrate that our methodology easily scales to many models. Across models, we find that the generated rhyme (e.g. "-ight") or answer to a question ("whale") can be manipulated by steering at the end of the preceding line with a vector, affecting the generation of intermediate tokens leading up to the rhyme or answer word. We show that implicit planning is a universal mechanism, present in smaller models than previously thought, starting from 1B parameters. Our methodology offers a widely applicable direct way to study implicit planning abilities of LLMs. More broadly, understanding planning abilities of language models can inform decisions in AI safety and control.

Computer Vision · Classification and Understanding

Alexander Baumann, Leonardo Ayala, Silvia Seidlitz, Jan Sellner, Alexander Studier-Fischer, Berkin Özdemir, Lena Maier-Hein, Slobodan Ilic

Spectral imaging offers promising applications across diverse domains, including medicine and urban scene understanding, and is already established as a critical modality in remote sensing. However, variability in channel dimensionality and captured wavelengths among spectral cameras impede the development of AI-driven methodologies, leading to camera-specific models with limited generalizability and inadequate cross-camera applicability. To address this bottleneck, we introduce CARL, a model for Camera-Agnostic Representation Learning across RGB, multispectral, and hyperspectral imaging modalities. To enable the conversion of a spectral image with any channel dimensionality to a camera-agnostic representation, we introduce a novel spectral encoder, featuring a self-attention-cross-attention mechanism, to distill salient spectral information into learned spectral representations. Spatio-spectral pre-training is achieved with a novel feature-based self-supervision strategy tailored to CARL. Large-scale experiments across the domains of medical imaging, autonomous driving, and satellite imaging demonstrate our model's unique robustness to spectral heterogeneity, outperforming on datasets with simulated and real-world cross-camera spectral variations. The scalability and versatility of the proposed approach position our model as a backbone for future spectral foundation models. Code and model weights are publicly available at https://github.com/IMSY-DKFZ/CARL.

Deep Learning · Graph Neural Networks

Joël Mathys, Henrik Christiansen, Federico Errica, Takashi Maruyama, Francesco Alesiani

Accurately modeling long-range dependencies in graph-structured data is critical for many real-world applications. However, incorporating long-range interactions beyond the nodes' immediate neighborhood in a $\textit{scalable}$ manner remains an open challenge for graph machine learning models. Existing benchmarks for evaluating long-range capabilities either cannot $\textit{guarantee}$ that their tasks actually depend on long-range information or are rather limited. Therefore, claims of long-range modeling improvements based on said performance remain questionable. We introduce the Long-Range Ising Model Graph Benchmark, a physics-based benchmark utilizing the well-studied Ising model whose ground truth $\textit{provably}$ depends on long-range dependencies. Our benchmark consists of ten datasets that scale from 256 to 65k nodes per graph, and provide controllable long-range dependencies through tunable parameters, allowing precise control over the hardness and ``long-rangedness". We provide model-agnostic evidence that local information is insufficient, further validating the design choices of our benchmark. Via experiments on classical message-passing architectures and graph transformers, we show that both perform far from the optimum, especially those with scalable complexity. Our goal is that our benchmark will foster the development of scalable methodologies that effectively model long-range interactions in graphs.

Computer Vision · Image and Video Generation

Youliang Zhang, Zhaoyang Li, Duomin Wang, jiahe zhang, Deyu Zhou, Zixin Yin, Xili Dai, Gang Yu, Xiu Li

The rapid development of large-scale models has catalyzed significant breakthroughs in the digital human domain. These advanced methodologies offer high-fidelity solutions for avatar driving and rendering, leading academia to focus on the next major challenge: audio-visual dyadic interactive virtual human. To facilitate research in this emerging area, we present SpeakerVid-5M dataset, the first large-scale, high-quality dataset designed for audio-visual dyadic interactive virtual human generation. Totaling over $8,743$ hours, SpeakerVid-5M contains more than $5.2$ million video clips of human portraits. It covers diverse scales and interaction types, including monadic talking, listening, and dyadic conversations. Crucially, the dataset is structured along two key dimensions: interaction type and data quality. First, it is categorized into four types (dialogue branch, single branch, listening branch and multi-turn branch) based on the interaction scenario. Second, it is stratified into a large-scale pre-training subset and a curated, high-quality subset for Supervised Fine-Tuning (SFT). This dual structure accommodates a wide array of 2D virtual human tasks. In addition, we provide an autoregressive (AR)-based video chat baseline trained on this data, accompanied by a dedicated set of metrics and test data to serve as a benchmark (VidChatBench) for future work. Both the dataset and the corresponding data processing code will be publicly released.

Deep Learning · Generative Models and Autoencoders

Christopher Ackerman

The possibility of LLM self-awareness and even sentience is gaining increasing public attention and has major safety and policy implications, but the science of measuring them is still in a nascent state. Here we introduce a novel methodology for quantitatively evaluating metacognitive abilities in LLMs. Taking inspiration from research on metacognition in nonhuman animals, our approach eschews model self-reports and instead tests to what degree models can strategically deploy knowledge of internal states. Using two experimental paradigms, we demonstrate that frontier LLMs introduced since early 2024 show increasingly strong evidence of certain metacognitive abilities, specifically the ability to assess and utilize their own confidence in their ability to answer factual and reasoning questions correctly and the ability to anticipate what answers they would give and utilize that information appropriately. We buttress these behavioral findings with an analysis of the token probabilities returned by the models, which suggests the presence of an upstream internal signal that could provide the basis for metacognition. We further find that these abilities 1) are limited in resolution, 2) emerge in context-dependent manners, and 3) seem to be qualitatively different from those of humans. We also report intriguing differences across models of similar capabilities, suggesting that LLM post-training may have a role in developing metacognitive abilities.

Applications · Time Series

Xiaokun Zhu, Louis Carpentier, Mathias Verbeke

Recent efforts have extended the foundation model paradigm from natural language to time series, raising expectations that pre-trained time-series foundation models generalize well across downstream tasks. In this work, we focus on time-series anomaly detection, in which time-series foundation models detect anomalies based on the reconstruction or forecasting error. Specifically, we critically examine the performance of five popular families of time-series foundation models: MOMENT, Chronos, TimesFM, Time-MoE, and TSPulse. We find that for each model family using varying model sizes and context window lengths, anomaly detection performance does not significantly differ to simple one-liner baselines: moving-window variance and squared-difference. These findings suggest that the key assumptions underlying reconstruction-based and forecasting-based methodologies for time-series anomaly detection are not satisfied for time-series foundation models: anomalies are not consistently harder to reconstruct or forecast. The results suggest that current approaches for leveraging foundation models in anomaly detection are insufficient. Building upon our insights, we propose alternative directions to effectively detect anomalies using foundation models, thereby unlocking their full potential for time-series anomaly detection.