论文检索

Reinforcement Learning · Deep RL

Raymond Chua, Doina Precup, Blake Richards

A hallmark of intelligence is the ability to adapt in non-stationary environments, yet deep Reinforcement Learning (RL) agents often struggle in such settings. Most prior studies introduce non-stationarity through abrupt shifts in features or dynamics, whereas real-world changes might be more gradual, reflecting naturalistic continual drift in the underlying dynamics. This may have important implications for studies on the "stability versus plasticity dilemma" in RL, since abrupt changes in the task may necessitate more plasticity than real-world situations actually would demand. To address these concerns, we modify existing 3D Miniworld and MuJoCo environments to incorporate naturalistic, continual non-stationary changes, and use them to identify whether poor performance in RL systems arises from a loss of plasticity or stability. We find that in these settings, methods that preserve stability, such as synaptic consolidation, achieve better performance than those focused on plasticity, such as resetting a subset of the parameters. Motivated by this finding, and prior evidence that successor features (SFs) reduce interference in non-stationary settings, we investigate whether SFs provide a better target than Q-values for consolidation. Across both environments, we find that applying a neuro-inspired synaptic consolidation mechanism to SFs rather than Q-values yields superior performance on the naturalistic, continual changing MuJoCo tasks. Furthermore, we find that consolidation is most effective when SFs are stabilized across multiple timescales, as different timescales capture complementary aspects of the gradually changing environment. Together, these results show that stability may be more important in continual learning settings when abrupt changes in tasks do not occur. Moreover, to enhance stability, multi-timescale consolidation of predictive representations is an effective approach.

Applications · Computer Vision

Yuxuan Zhou, Baole Wei, Xingjian Hu, Haowei Chen, Yu Li, Xingyue Lin, Liangcai Gao, Zhi Tang

Real-world degradations, such as noise, blur, and low resolution, significantly impair the performance of Multi-modal Large Language Models (MLLMs) in document understanding tasks. Despite recent advancements, progress in this field remains stifled by two critical bottlenecks: the scarcity of large-scale, aligned training data necessary for learning robustness, and the lack of transferable restoration solutions across diverse MLLM architectures. To bridge the data gap, we first present DocRobust-VQA, a large-scale dataset explicitly constructed to support robustness training. Comprising 189K aligned low/high-quality document image pairs and 417K QA pairs, it provides the first substantial corpus for fine-tuning MLLMs to handle varying degradation conditions. Leveraging this data, we propose Uni-DocRobust, a universal plug-and-play framework that decouples restoration capabilities from specific visual encoders. Our method employs a frozen Universal Restoration Core pre-trained in a canonical feature space via multi-teacher distillation, which can be seamlessly integrated into target MLLMs (e.g., Qwen-VL, InternVL) through lightweight Feature Adapters. Extensive experiments demonstrate that Uni-DocRobust significantly enhances robust performance on MLLMs and enables a cost-effective ``pre-train once, deploy everywhere'' paradigm for robust MLLM deployment.

Deep Learning · Theory

Florian Handke, Dejan Stancevic, Felix Koulischer, Thomas Demeester, Luca Ambrogioni

Diffusion models do not recover semantic structure uniformly over time. Instead, samples transition from semantic ambiguity to class commitment within a narrow regime. Recent theoretical work attributes this transition to dynamical instabilities along class-separating directions, but practical methods to detect and exploit these windows in trained models are still limited. We show that tracking the class-conditional entropy of a latent semantic variable given the noisy state provides a reliable signature of these transition regimes. By restricting the entropy to semantic partitions, the entropy can furthermore resolve semantic decisions at different levels of abstraction. We analyze this behavior in high-dimensional Gaussian mixture models and show that the entropy rate concentrates on the same logarithmic time scale as the speciation symmetry-breaking instability previously identified in variance-preserving diffusion. We validate our method on EDM2-XS and Stable Diffusion 1.5, where class-conditional entropy consistently isolates the noise regimes critical for semantic structure formation. Finally, we use our framework to quantify how guidance redistributes semantic information over time. Together, these results connect information-theoretic and statistical physics perspectives on diffusion and provide a principled basis for time-localized control.

Probabilistic Methods · Bayesian Models and Methods

Arjun Mani, Carl Vondrick, Richard Zemel

Many real-world design problems involve optimizing an expensive black-box function $f(x)$, for which Bayesian Optimization is a sample-efficient framework. However, while the basic black-box setting returns a scalar reward, real-world experiments often generate a wealth of useful information. We introduce a new setting where an experiment generates high-dimensional auxiliary information $h(x)$ along with $f(x)$; moreover, a history of relevant, previously-solved tasks is available for accelerating optimization. We develop a novel method based on a neural model which predicts $f(x)$ for unseen designs given a few-shot context containing observations of $h(x)$. We evaluate our method on two challenging domains, robotic hardware design and hyperparameter tuning. On both domains, our method achieves improved few-shot prediction and faster design optimization, outperforming several multi-task optimization methods.

Applications · Chemistry, Physics, and Earth Sciences

Sepehr Mousavi, Siddhartha Mishra, Laura De Lorenzis

Neural operators have emerged as powerful surrogates for the solution of partial differential equations (PDEs), yet their ability to handle general, highly variable boundary conditions (BCs) remains limited. Existing approaches often fail when the solution operator exhibits strong sensitivity to boundary forcings. We propose a general framework for conditioning neural operators on complex non-homogeneous BCs through function extensions. Our key idea is to map boundary data to latent pseudo-extensions defined over the entire spatial domain, enabling any standard operator learning architecture to consume boundary information. The resulting operator, coupled with an arbitrary domain-to-domain neural operator, can learn rich dependencies on complex BCs and input domain functions at the same time. To benchmark this setting, we construct 18 challenging datasets spanning Poisson, linear elasticity, and hyperelasticity problems, with highly variable, mixed-type, component-wise, and multi-segment BCs on diverse geometries. Our approach achieves state-of-the-art accuracy, outperforming baselines by large margins, while requiring no hyperparameter tuning across datasets. Overall, our results demonstrate that learning boundary-to-domain extensions is an effective and practical strategy for imposing complex BCs in existing neural operator frameworks, enabling accurate and robust scientific machine learning models for a broader range of PDE-governed problems.

General Machine Learning · Data

Nick Jiang, Xiaoqing Sun, Lisa Dunlap, Lewis Smith, Neel Nanda

Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors. Current methods often rely on costly LLM-based techniques (e.g. annotating dataset differences) or dense embedding models (e.g. for clustering), which lack control over the properties of interest. We propose using sparse autoencoders (SAEs) to create *SAE embeddings*: representations whose dimensions map to interpretable concepts. Through four data analysis tasks, we show that SAE embeddings are more cost-effective and reliable than LLMs and offer the controllability that dense embeddings lack. Using the large hypothesis space of SAEs, we can uncover insights such as (1) semantic differences between datasets and (2) unexpected concept correlations in documents. For instance, by comparing model responses, we find that Grok-4 clarifies ambiguities more often than nine other frontier models. Relative to LLMs, SAE embeddings uncover bigger differences at 2-8x lower cost and identify biases more reliably. Additionally, SAE embeddings are controllable: by filtering concepts, we can (3) cluster documents along axes of interest and (4) outperform dense embeddings on property-based retrieval. Using SAE embeddings, we study model behavior with two case studies: investigating how OpenAI model behavior has changed over time and finding "trigger" phrases learned by Tulu-3 (Lambert et. al., 2024) from its training data. These results position SAEs as a versatile tool for unstructured data analysis and highlight the neglected importance of interpreting models through their *data*.

Deep Learning · Large Language Models

Yingsheng Geng, Yuchong Gao, Weihong Wu, Guyue Liu, Jiang liu

The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectures introduce a critical bottleneck: redundant prefill computation for shared content generated by previous agents, which significantly increases KV cache memory usage and time-to-first-token (TTFT). While various KV cache methods have been proposed to mitigate prefill redundancy, they either fail to maintain accuracy on agent-generated outputs or exhibit low reuse rates due to rigid constraints. We present RelayCaching, a training-free inference method that directly reuses decoding phase KV caches from previous agents in subsequent prefill phases. Our key insight is that KV caches for identical content are highly consistent across phases, while prefix-induced deviations are sparse and localized within a limited range of layers and token positions. By selectively recomputing KV caches at these positions, RelayCaching preserves model accuracy with minimal overhead, yielding a superior accuracy–efficiency trade-off over existing methods. Experiments on diverse collaborative LLM tasks spanning mathematical reasoning, general knowledge, and code generation demonstrate that RelayCaching achieves over $80$\% KV cache reuse, reduces TTFT by up to $4.7\times$ compared to the standard pipeline, all with negligible accuracy degradation.

General Machine Learning · Representation Learning

Yulin Zhang, Boxuan Hu, Huimin Li, Junlin Hu

Hyperbolic metric learning is highly effective in embedding hierarchical data structures. However, past work has predominantly focused on the conformal Poincaré model, leaving other geometries like the Klein model largely under-explored. In addition, the curved geodesics of the Poincaré model present a fundamental geometric misalignment with the linear projections dominating the feature transformation steps in the modern neural network backbones. In this paper, we investigate the Klein model, a projective model of hyperbolic geometry whose straight-line geodesics offer a structurally aligned alternative in linear encoders, for hyperbolic metric learning. By formalizing a framework based on Einstein gyrovector operations, we derive a numerically stable metric learning approach that mitigates the inherent optimization challenges of the Klein model. Extensive experiments on multiple image datasets for fine-grained image classification task show that the Klein model not only serves as a viable alternative to the Poincaré model but also achieves highly competitive performance by leveraging its unique geometric properties, without increasing parameter complexity. Our empirical findings establish the Klein model as an efficient geometric prior for hyperbolic metric learning.

Optimization · Zero-order and Black-box Optimization

Boris Prokhorov, Semyon Chebykin, Alexander Gasnikov, Aleksandr Beznosikov

This paper deals with stochastic optimization problems involving Markovian noise with a zero-order oracle. We present and analyze a novel derivative-free method for solving such problems in strongly convex smooth and non-smooth settings with both one-point and two-point feedback oracles. Using a randomized batching scheme, we show that when mixing time $\tau$ of the underlying noise sequence is less than the dimension of the problem $d$, the convergence estimates of our method do not depend on $\tau$. This observation provides an efficient way to interact with Markovian stochasticity: instead of invoking the expensive first-order oracle, one should use the zero-order oracle. Finally, we complement our upper bounds with the corresponding lower bounds. This confirms the optimality of our results.

Applications · Computer Vision

Wenhao Zou, Zhijie Cai, Minchen Yu, Zongshuai Zhang, Guangxu Zhu

Long video understanding faces a critical dilemma: cloud-based Large Multimodal Models (LMMs) offer superior reasoning but suffer from prohibitive bandwidth costs and latency, while edge-based solutions sacrifice perception accuracy for speed. Current collaborative approaches attempt to bridge this gap via similarity-based filtering, yet they treat complex queries as flat semantic vectors. We identify this as a fundamental flaw leading to "Semantic Submergence," where dominant visual features drown out subtle but logically critical cues. To solve this, we introduce SCOPE (Semantic Cloud-Orchestrated Perception at Edge). Shifting the paradigm to "Think in Cloud, Look at Edges," SCOPE utilizes a cloud LMM to decompose complex queries into a structured Directed Acyclic Graph (DAG). This "observation plan" guides the edge to retrieve evidence based on logical necessity rather than mere statistical similarity. Experiments on Video-MME and LongVideoBench demonstrate that SCOPE redefines the Pareto frontier, matching cloud-level accuracy with significantly lower transmission costs and outperforming state-of-the-art baselines on complex reasoning tasks.

Deep Learning · Generative Models and Autoencoders

Gwangho Kim, Sungyoon Lee

Diffusion models can unintentionally memorize training samples, raising concerns about privacy and copyright. While recent methods can detect memorization, they often rely on global or model-specific signals and provide limited insight into where memorization appears within a generated image. We provide a geometric characterization of local memorization as a coordinate-wise variance collapse. However, such collapse can also arise from intrinsic data constraints rather than overfitting. To isolate overfitting-driven memorization, we propose curvature-difference methods that subtract the curvature of an underfitted baseline, either the unconditional model or a less-trained version of itself. We further derive a score-difference surrogate that provides a geometric explanation for the widely used score-difference-based detection metric. Experiments on Stable Diffusion, evaluated against ground-truth memorization masks, show that our method outperforms the prior attention-based localization method.

Optimization · Zero-order and Black-box Optimization

Zhijie Cai, Haolong Chen, Guangxu Zhu

Fine-tuning LLMs is necessary for various dedicated downstream tasks, but classic backpropagation-based fine-tuning methods require substantial GPU memory. To this end, a recent work, MeZO, which relies solely on forward passes to fine-tune LLMs, significantly reduces GPU requirements at the cost of slower convergence due to its indifference to loss landscapes. Standard solutions, such as Adam, explore loss landscapes by estimating the first- and second-order moments and storing them in memory to guide the model's movement through dimensions with lower curvature and vice versa. However, directly applying Adam negates MeZO's advantage as it will triple the memory requirement. In light of this, we propose AdaMeZO, a zeroth-order optimizer that leverages Adam-style first- and second-moment estimates without maintaining them in memory. We present a theoretical analysis of AdaMeZO, corroborated by extensive experiments demonstrating its performance, showing that it can outperform MeZO while requiring up to 70% fewer forward passes. Trajectory visualizations affirm AdaMeZO's ability to adapt to diverse loss landscapes.

Applications · Language, Speech and Dialog

Jinhao Duan, Ruichen Zhang, Gengwei Zhang, Huaizhi Qu, Jie Peng, Sijia Liu, Tianlong Chen

Though biological foundation models (Bio-FMs) have delivered strong performance across biomedical tasks, their robustness to small-but-real perturbations is underexplored. In this work, we ask: Are Bio-FMs robust for real-world use? What perturbations compromise their reliability? Our pilot study suggests that due to subtle biological data curation issues and common machine-learning (ML) processing choices, Bio-FMs suffer from two complementary perturbation sources: biologically plausible perturbations (capturing experimental corruptions and curation artifacts) and ML-induced transformations (capturing preprocessing, data augmentation, and embedding choices). Guided by this taxonomy, we design perturbation suites that mimic corruptions frequently encountered in biological experiments, and we systematically probe how transformations in the ML pipeline reshape model behavior. By conducting 2,128 experiments over 11 state-of-the-art Bio-FMs on 7 bio-tasks, we show that most Bio-FMs are vulnerable to both biological perturbations and ML transformations, revealing underappreciated robustness gaps that can directly translate into deployment risk. Interestingly, we find that subtle biological perturbations, which are often imperceptible to current measurement tools, can induce severe discrepancies in Bio-FM outputs and lead to critical failures. We also find that cryo-EM reconstruction models (e.g., CryoDRGN) exhibit a surprising level of robustness even under worst-case adversarial settings. Our study for the first time surfaces critical failure modes and provides a principled perspective for evaluating the robustness of Bio-FMs in real-world biological pipelines.

Social Aspects · Security

Yuhao Wang, Shengfang ZHAI, Guanghao Jin, Yinpeng Dong, Linyi Yang, Jiaheng Zhang

Large Language Model (LLM)-based agents employ external and internal memory systems to handle complex, goal-oriented tasks, yet this exposes them to severe extraction attacks, and corresponding defenses are currently lacking. In this paper, we propose *MemPot*, the first theoretically verified defense framework against memory extraction attacks by injecting optimized honeypots into the memory. Through a two-stage optimization process, *MemPot* generates trap documents that maximize the retrieval probability for attackers while remaining inconspicuous to benign users. We model the detection process as Wald’s Sequential Probability Ratio Test (SPRT) and theoretically prove that *MemPot* achieves a lower average number of sampling rounds compared to optimal static detectors. Empirically, *MemPot* significantly outperforms state-of-the-art baselines, achieving a 50% improvement in detection AUROC and an 80% increase in True Positive Rate under low False Positive Rate constraints. Furthermore, our experiments confirm that *MemPot* incurs zero online inference latency and preserves the agent's utility on standard tasks, verifying its superiority in safety, harmlessness and efficiency.

Deep Learning · Large Language Models

Jinhao Duan, Zicheng Liu, Zijie Liu, Kaidi Xu, Tianlong Chen

Humans express uncertainty verbally via markers (e.g., "possible", "likely"), yet most LLM uncertainty quantification (UQ) relies on costing likelihood- or consistency-based signals. From a cognitive perspective, accurate verbal uncertainty reflects metacognitive monitoring, representing knowledge boundaries ("knowing that you don't know") to support regulation and information seeking. In this paper, we investigate: How LLMs diverge from humans in verbal uncertainty quantification? Can verbal markers reliably quantify LLM uncertainty? We curate a corpus of human uncertainty markers from psychology and decision-science literature and benchmark LLMs against it. We observe that LLMs encode verbal uncertainty with numerical levels that differ substantially from those of humans. We then introduce VOCAL, a novel optimization-based algorithm that learns an optimal uncertainty profile over uncertainty markers directly from LLM outputs. By fitting a marker–uncertainty mapping to best explain empirical correctness, VOCALdiscovers how much probability mass each verbal marker should convey, rather than estimating uncertainty via repeated sampling. VOCAL enables a direct, marker-level comparison of confidence semantics between humans and LLMs, disentangling mismatch and revealing systematic confidence disparities in verbal expressions.

Theory · Game Theory

Annalisa Barbara, Riccardo Poiani, Martino Bernasconi, Andrea Celli

We study a setting in which two players play a (possibly approximate) Nash equilibrium of a bimatrix game, while a learner observes only their actions and has no knowledge of the equilibrium or the underlying game. A natural question is whether the learner can rationalize the observed behavior by inferring the players' payoff functions. Rather than producing a single payoff estimate, inverse game theory aims to identify the entire set of payoffs consistent with observed behavior, enabling downstream use in, e.g., counterfactual analysis and mechanism design across applications like auctions, pricing, and security games. We focus on the problem of estimating the set of feasible payoffs with high probability and up to precision $\epsilon$ on the Hausdorff metric. We provide the first minimax-optimal rates for both exact and approximate equilibrium play, in zero-sum as well as general-sum games. Our results provide learning-theoretic foundations for set-valued payoff inference in multi-agent environments.

Deep Learning · Generative Models and Autoencoders

Thomas Sesmat, Gabriel Meseguer-Brocal, Geoffroy Peeters

Understanding what generative models retain from training data remains challenging, with implications for copyright and privacy. This question becomes particularly relevant as Rectified Flows power increasingly deployed systems. We analyze the interpolation path $X_\lambda = (1-\lambda)X_0 + \lambda X_1$ that defines Rectified Flow training. We show that train-test distinguishability follows a bell-shaped curve over $\lambda$, with a maximum whose location we derive in closed form under Gaussian assumptions. This signal accumulates during training while validation metrics remain stable. We validate these predictions on both audio and images, and show that the bell-shaped structure is universal while the peak prediction holds when our assumptions are satisfied. As a proof of concept, we implement a membership inference attack achieving 0.91 AUC by exploiting this $\lambda$-resolved structure.

General Machine Learning · Representation Learning

Damion Harvey, Steven James, Benjamin Rosman, Branden Ingram, Geraud Nangue Tasse

We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent approaches have sought to segment trajectories into reusable skills or options, most rely on action labels, rewards, or handcrafted annotations, limiting their applicability. We propose a method that segments unlabelled trajectories into skills and induces a hierarchical structure over them using a grammar-based approach. The resulting hierarchy captures both low-level behaviours and their composition into higher-level skills. We evaluate our approach in high-dimensional, pixel-based environments, including Craftax and the full, unmodified version of Minecraft. Using metrics for skill segmentation, reuse, and hierarchy quality, we find that our method consistently produces more structured and semantically meaningful hierarchies than existing baselines. Furthermore, as a proof of concept for utility, we demonstrate that these discovered hierarchies accelerate and stabilise learning on downstream reinforcement learning tasks.

Applications · Computer Vision

Shaoxiong Zhan, Yanlin Lai, Zheng Liu, Zijian Lin, Lin Hai, Xiaodong Cai, Shen Li, Wen Huang, Hai-Tao Zheng

Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical "spatial intelligence gap," where models fail to construct coherent 3D mental representations from 2D observations. We uncover this gap via diagnostic analyses showing the bottleneck is a missing view-consistent spatial interface rather than insufficient visual features or weak reasoning. To bridge this, we introduce **3ViewSense**, a framework that grounds spatial reasoning in Orthographic Views. Drawing on engineering cognition, we propose a "Simulate-and-Reason" mechanism that decomposes complex scenes into canonical orthographic projections to resolve geometric ambiguities. By aligning egocentric perceptions with these allocentric references, our method facilitates explicit mental rotation and reconstruction. Empirical results on spatial reasoning benchmarks demonstrate that our method significantly outperforms existing baselines, with consistent gains on occlusion-heavy counting and view-consistent spatial reasoning. The framework also improves the stability and consistency of spatial descriptions, offering a scalable path toward stronger spatial intelligence in multimodal systems.

Shaoxiong Zhan, Yanlin Lai, Zheng Liu, Zijian Lin, Lin Hai, Xiaodong Cai, Shen Li, Wen Huang, Hai-Tao Zheng

Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical "spatial intelligence gap," where models fail to construct coherent 3D mental representations from 2D observations. We uncover this gap via diagnostic analyses showing the bottleneck is a missing view-consistent spatial interface rather than insufficient visual features or weak reasoning. To bridge this, we introduce **3ViewSense**, a framework that grounds spatial reasoning in Orthographic Views. Drawing on engineering cognition, we propose a "Simulate-and-Reason" mechanism that decomposes complex scenes into canonical orthographic projections to resolve geometric ambiguities. By aligning egocentric perceptions with these allocentric references, our method facilitates explicit mental rotation and reconstruction. Empirical results on spatial reasoning benchmarks demonstrate that our method significantly outperforms existing baselines, with consistent gains on occlusion-heavy counting and view-consistent spatial reasoning. The framework also improves the stability and consistency of spatial descriptions, offering a scalable path toward stronger spatial intelligence in multimodal systems.