论文检索

Deep Learning · Generative Models and Autoencoders

Dongjiang Niu, Xiaofeng Wang, Zhiqiang Wei, Zhen Li

Although peptides are well suited for flexible and shallow binding interfaces, their intrinsic flexibility induces a strongly coupled sequence–structure relationship that current fixed-geometry latent models cannot simultaneously model with conformational diversity and physical feasibility, ultimately limiting design quality. To overcome this bottleneck, PepFGLD is proposed as a receptor-conditioned, flexibility-aware framework for full-atom peptide design. The framework is motivated by a systematic analysis of existing limitations: geometry shifts driven by interfacial flexibility are not well captured by standard equivariant encoders; the static combination of sequence information and 3D geometry cannot represent their dynamic interactions; and diffusion models without timely geometric feedback tend to drift away from physically reasonable energy landscapes. In PepFGLD, FlexEGNN is used to improve the sensitivity of geometric representations to local flexibility, a coherent and adaptable latent conformational manifold is formed through bidirectional sequence–structure interaction and nonlinear latent mapping, and a time-dependent energy-guided diffusion mechanism is incorporated to balance exploration and convergence during diffusion so that sampling trajectories are continuously guided toward physically feasible full-atom structures. PepFGLD yields improved binding affinity and design success across multiple peptide design tasks.

Reinforcement Learning · Online

MohammadHossein Rezaei, Robert Vacareanu, Zihao Wang, Clinton Wang, Bing Liu, Yunzhong He, Afra Feyza Akyürek

Rubrics provide a flexible way to train LLMs on open-ended long-form answers where verifiable rewards are not applicable and human preferences provide coarse signals. Prior work shows that reinforcement learning with rubric-based rewards leads to consistent gains in LLM post-training. Most existing approaches rely on rubrics that remain static over the course of training. Such static rubrics, however, are vulnerable to reward-hacking type behaviors and fail to capture emergent desiderata that arise during training. We introduce Online Rubrics Elicitation (OnlineRubrics), a method that dynamically curates evaluation criteria in an online manner through pairwise comparisons of responses from current and reference policies. This online process enables continuous identification and mitigation of errors as training proceeds. Empirically, this approach yields consistent improvements of up to 8% over training exclusively with static rubrics across AlpacaEval, GPQA, ArenaHard as well as the validation sets of expert questions and rubrics. We qualitatively analyze the elicited criteria and identify prominent themes such as transparency, practicality, organization, and reasoning.

Reinforcement Learning · Online

Sheelabhadra Dey, Guni Sharon

Gaussian Mixture Models (GMMs) have been recently proposed for approximating actors in actor-critic reinforcement learning algorithms. Such GMM-based actors are commonly optimized using stochastic policy gradients along with an entropy maximization objective. In contrast to previous work, we define and study deterministic policy gradients for optimizing GMM-based actors. Similar to stochastic gradient approaches, our proposed method, denoted $\textit{Gaussian Mixture Deterministic Policy Gradient}$ (Gamid-PG), encourages policy entropy maximization. To this end, we define the GMM entropy gradient using $\textit{Variational Approximation}$ of the $KL$-divergence between the GMM's constituting Gaussians. We compare Gamid-PG with common stochastic policy gradient methods on benchmark dense-reward MuJoCo tasks and sparse-reward Fetch tasks. We observe that Gamid-PG outperforms stochastic gradient-based methods in 3/6 MuJoCo tasks while performing similarly on the remaining 3 tasks. In the Fetch tasks, Gamid-PG outperforms single-actor deterministic gradient-based methods while performing worse than stochastic policy gradient methods. Consequently, we conclude that GMMs optimized using deterministic policy gradients (1) should be favorably considered over stochastic gradients in dense-reward continuous control tasks, and (2) improve upon single-actor deterministic gradients.

Applications · Health / Medicine

Alma Andersson, Aya Ismail, Edward De Brouwer, Doron Haviv, Tommaso Biancalani, Kyunghyun Cho, Gabriele Scalia, Aicha BenTaieb, Hector Corrada Bravo

Understanding cellular phenotypes and how they respond to perturbations is critical for disease biology and therapeutic design. Single-cell RNA sequencing enables characterization at cellular resolution, yet the combinatorial space of conditions makes exhaustive experimental mapping infeasible. We introduce single-cell Concept Bottleneck Generative Models (scCBGM), a framework for interpretable and precise counterfactual editing of individual cells. scCBGM adapts concept bottleneck architectures for single-cell data through decoder skip connections and a cross-covariance penalty that promotes disentanglement without dimensional constraints. We extend the framework to flow matching models, enabling concept-guided editing in both encoding-decoding and generation regimes. To enable rigorous evaluation, we develop a synthetic benchmark with ground-truth counterfactuals. Across multiple real datasets, scCBGM demonstrates superior accuracy in zero-shot generalization and cell-level counterfactual prediction compared to state-of-the-art methods, while providing interpretable control over biological concepts.

Applications · Computer Vision

Chunyang Li, Haoyue Wang, Zhenxing Qian, Sheng Li, Xinpeng Zhang, Jian liu, Yixuan Pei, Weiqiang Wang

Identifiable virtual face (IVF) generation aims to transform a user's original face into a virtual face for high utility privacy protection. The IVF is visually and statistically different from the original face, which can still be used for recognizing the user's identity. Despite the advantage, these schemes are unable to verify the trustworthiness of the IVF, the quality and controllability of which is often limited. To address these issues, we propose TIVDiff, a diffusion-based framework for trustworthy and identifiable virtual face generation. TIVDiff learns a virtual identity (VID) space via Virtual Identity Projection (VIP) and synthesizes high-quality virtual faces conditioned on VID and 3D facial geometry for pose and expression preservation. To enable the trustworthiness of IVF, we introduce Identity-Guarded Generative Watermarking (IGGW) to bind the diffusion initial noise with VID through a reversible mapping. This enables the embedding of an imperceptible cue into IVF for legitimacy verification. Experiments demonstrate the advantage of our TIVDiff over the state-of-the-art IVF generation schemes in terms of image quality, identifiability and trustworthiness.

Reinforcement Learning · Multi-agent

Yizhou Zhang, Eric Mazumdar

Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary strategies are preferred for their practicality, computing stationary forms of classic game-theoretic equilibria is computationally intractable—a stark contrast to the comparative ease of solving single-agent RL or zero-sum games. To bridge this gap, we study Risk-averse Quantal response Equilibria (RQE), a solution concept rooted in behavioral game theory that incorporates risk aversion and bounded rationality. We demonstrate that RQE possesses strong regularity conditions that make it uniquely amenable to learning in MGs. We propose a novel two-timescale Actor-Critic algorithm characterized by a fast-timescale actor and a slow-timescale critic. Leveraging the regularity of RQE, we prove that this approach achieves global convergence with finite-sample guarantees. We empirically validate our algorithm in several environments to demonstrate superior convergence properties compared to risk-neutral baselines.

Reinforcement Learning · Multi-agent

ZEYI SUN, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Tong Wu, Dahua Lin, Jiaqi Wang

Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models often struggle with novel and specialized software, particularly in scenarios lacking human annotations. To address this challenge, we propose SEAgent, an agentic self-evolving framework enabling CUAs to autonomously evolve through interactions with unfamiliar software. Specifically, SEAgent empowers computer-use agents to autonomously master novel software environments via experiential learning, where agents explore new software, learn through iterative trial-and-error, and progressively tackle auto-generated tasks organized from simple to complex. To achieve this goal, we design a World State Model for step-wise trajectory assessment, along with a Curriculum Generator that generates increasingly diverse and challenging tasks. The agent's policy is updated through experiential learning, comprised of adversarial imitation of failure actions and Group Relative Policy Optimization (GRPO) on successful ones. Furthermore, we introduce a specialist-to-generalist training strategy that integrates individual experiential insights from specialist agents, facilitating the development of a stronger generalist CUA capable of continuous autonomous evolution. This unified agent ultimately achieves performance surpassing ensembles of individual specialist agents on their specialized software. We validate the effectiveness of SEAgent across five professional software of OSWorld, ScienceBoard and AndroidWorld. Our approach achieves a significant improvement over a competitive open-source CUA, UI-TARS. All the code and models will be made publicly available to foster further research.

Reinforcement Learning · Batch/Offline

Yunpeng Qing, Yixiao Chi, Shuo Chen, Shunyu Liu, Kexuan Zhou, Sixu Lin, Litao Liu, Changqing Zou

Offline Reinforcement Learning (RL) relies on static datasets and often enforces conservative constraints to mitigate out-of-distribution errors, but this inevitably gives rise to learning dataset biases and limited behavioral generalization. Recent Data Augmentation (DA) methods leverage generative models to enrich offline data, yet they mainly operate within a single rollout paradigm and tend to preserve the original trajectory-level connectivity of the dataset. As a result, such methods often introduce local variations and fail to recover connections between distinct behavior patterns. In this paper, we propose Bidirectional Trajectory Diffusion (BiTrajDiff), a novel DA framework that explicitly addresses this limitation. BiTrajDiff decomposes trajectory synthesis into two independent diffusion processes that generate forward-future and backward-history segments conditioned on shared intermediate anchor states. By stitching the generated segments at these anchors, BiTrajDiff can synthesize trajectories that bridge disconnected behavior patterns and recover global trajectory-level connectivity absent from the original data. Extensive experiments on the D4RL benchmark demonstrate that BiTrajDiff consistently outperforms advanced DA methods across a range of offline RL backbones.

Applications · Everything Else

Hongru Hou, Tiehua Mei, Denghui Geng, Jinhui Huang, Ao Xu, Hengrui Chen, Jiaqing Liang, Deqing Yang

Proactive Recommender Systems (PRSs) aim to guide user preference shift toward target items by generating paths of intermediate recommendations. Reinforcement learning (RL) provides a principled framework for optimizing such sequential decision tasks. Based on path rewards, RL can naturally jointly optimize short-term acceptance and long-term guidance effectiveness. However, naively applying policy gradients to PRS results in deficient gradient estimation. It has been observed that length-dependent bias causes gradients to favor path extension over deeper exploration, while weighting each step by path-level reward leads to high gradient variance. To rectify these two deficiencies, we propose an effective RL framework $\textbf{ProRL}$ with two novel mechanisms for proactive recommendation. First, Stepwise Reward Centering subtracts expected rewards to neutralize length-dependent bias, ensuring that path extension yields zero expected gradient signal. Second, Position-Specific Advantage Estimation leverages the reward decomposition structure to compute step-dependent baselines, reducing gradient variance. Together, these mechanisms yield policy gradients that precisely target path quality. Our experiments on three real-world datasets demonstrate that ProRL significantly outperforms state-of-the-art PRSs. Our codes are available at https://anonymous.4open.science/r/ProRL-D56DHM.

Applications · Everything Else

Binhao Gu, jinjun cai, Weihuang Zheng, Jiaxing Li, Hui Ding, Youyong Kong

Multi-Agent Reinforcement Learning (MARL) has been widely applied to automated aircraft conflict resolution due to its strong capability for cooperative control and distributed decision-making. However, existing approaches typically assume a fixed number of aircraft and neglect the unique characteristics of air traffic control instructions. This structural misalignment between model architectures and domain requirements leads to severe deficiencies in perception scalability and action stability across scenarios of varying scales. To address these challenges, we propose Structural-Aligned Reinforcement Learning (SARL), which aims to bridge the gap between perception and action. First, the Physically Encoded Relational Graph (PERG) effectively resolves the fixed input dimensionality issue by incorporating physical inductive biases into a graph attention mechanism. Second, we design the Sparse Cognitive Mixture-of-Experts (SC-MoE) to enhance decision stability. In addition, we introduce a Kinematic Kafety Shield (KSS) based on aviation rules, which not only improves inference-time safety but also effectively guides the model to generate semantically meaningful actions that comply with aviation standards. Simulation experiment results demonstrate that SARL significantly outperforms existing reinforcement learning baselines across diverse scenarios in terms of both success rate and operational efficiency.

Applications · Chemistry, Physics, and Earth Sciences

Wenjie Luo, chaorong li, Chuanhu Deng, Zhuo Wang

Reliable long-horizon precipitation nowcasting requires preserving fine-scale echo structures while maintaining coherent transport. Although Rectified Flow (RF) can generate detail-preserving future sequences, numerical ODE integration compounds velocity estimation errors and induces progressive off-manifold drift, causing morphological distortions at extended lead times. We propose Physically-guided Data-space Rectified Flow (PDRF), which re-parameterizes the generative ODE in data space: the network predicts the clean future sequence, analytically inducing a coupled vector field with an implicit restoring effect that suppresses drift. We also introduce a soft Semi-Lagrangian teacher based on an advection prior to regularize large-scale transport, while allowing local growth/decay/deformation to be learned from data. Experiments on four public benchmarks demonstrate consistent improvements in event-based skill and better preservation of intense-echo morphology over long horizons.

Applications · Everything Else

Jiajing Xu, Yanyun Li, Songyongbao, Minqin Zhu, Huxiao Ji, Linchuan Li, Cunyi Zhang, lixuanping, Kaiqiao Zhan, Yanan Niu

Notification dispatch plays a critical role in large-scale user engagement, involving complex trade-offs across notification timing, presentation style, multiple outcomes, and constraints. In this paper, we formulate it as a constrained optimization over bundle treatments that jointly specify timing and presentation style, aiming to maximize incremental Daily Active Users (DAU) subject to platform-level budget and device vendor-specific quota constraints. The problem is challenging due to multi-dimensional, small-effect uplift estimation and large-scale constrained optimization. To address these challenges, we propose $\textbf{B}$undle $\textbf{U}$plift $\textbf{O}$ptimization with $\textbf{P}$runed $\textbf{L}$agrangian-based $\textbf{R}$elaxation (BUOPLR), a two-stage notification dispatch method that decouples uplift estimation from constrained decision-making. BUOPLR first learns bundle-level, multi-outcome small uplift through an architecture that captures cross-treatment and cross-outcome relationships, and then performs scalable assignment by restricting the decision space and applying Lagrangian relaxation to a small set of global constraints. Offline experiments show BUOPLR outperforms state-of-the-art methods, and online A/B tests increase DAU by 0.5\%. BUOPLR is now deployed on a major Internet platform serving over 100 million users daily.

Reinforcement Learning · Deep RL

Elizabeth Bates, Chris Hicks, Vasilios Mavroudis

Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning. These agents are typically trained in cyber gym environments using dense, highly engineered reward functions which combine many penalties and incentives for a range of (un)desirable states and costly actions. Dense rewards help alleviate the challenge of exploring complex environments but risk biasing agents towards suboptimal and potentially riskier solutions, a critical issue in complex cyber environments. We thoroughly evaluate the impact of reward function structure on learning and policy behavioural characteristics using a variety of sparse and dense reward functions, two well-established cyber gyms, a range of network sizes, and both policy gradient and value-based RL algorithms. Our evaluation is enabled by a novel ground truth evaluation approach which allows directly comparing between different reward functions, illuminating the nuanced inter-relationships between rewards, action space and the risks of suboptimal policies in cyber environments. Our results show that sparse rewards, provided they are goal aligned and can be encountered frequently, uniquely offer both enhanced training reliability and more effective cyber defence agents with lower-risk policies. Surprisingly, sparse rewards can also yield policies that are better aligned with cyber defender goals and make sparing use of costly defensive actions without explicit reward-based numerical penalties.

Applications · Everything Else

Ruizhe Zhong, Xingbo Du, Junchi Yan

Floorplanning determines the coordinate and shape of each module in Integrated Circuit. With the advancement of technology node, in floorplanning stage especially 3D scenarios with multiple stacked layers, it has become increasingly challenging to adhere to complex hardware design rules. Current methods are only capable of handling specific and limited design rules, while violations of other rules require manual and meticulous adjustment. This leads to labor-intensive and time-consuming post-processing for expert engineers. In this paper, we propose an all-in-one deep reinforcement learning-based approach to tackle these challenges, and design novel representations for real-world IC design rules that have not been addressed by previous approaches. Specifically, the processing of various hardware design rules is unified into a single framework with three key components: 1) novel matrix representations to model the design rules, 2) constraints on the action space to filter out invalid actions that cause rule violations, and 3) quantitative analysis of constraint satisfaction as reward signals. Experiments on public benchmarks demonstrate the effectiveness and validity of our approach. Furthermore, transferability are well shown on unseen circuits. Our framework is extensible to accommodate new design rules, thus providing flexibility to address emerging challenges in future chip design.

Applications · Everything Else

Zhe Xiao, Longfei Li, Xu He, Haoying Wu, Zixing Zhang, Mingyu Liu

Symbolic expressions can effectively characterize and predict circuit behavior, but deriving them directly from circuit schematics is challenging. This process requires accurate visual-to-symbolic construction of circuit structure from images and correct multi-step symbolic derivation, both of which impose strict correctness requirements. This work proposes AutoVSR, an automated framework for visual-to-symbolic generation of circuit expressions using Vision Language Models (VLMs). By reconstructing circuit diagrams into an executable intermediate representation (Executable IR) and leveraging a symbolic solver for reasoning, AutoVSR significantly improves the accuracy of symbolic expression generation. AutoVSR introduces two key innovations: an IR construction method guided by component rule retrieval and verification-based feedback, and a symbolic solver implemented as a planning agent equipped with a symbolic tool library for reliable multi-step derivation. Compared to end-to-end VLM approaches, AutoVSR achieves accuracy improvements of 30.01--59.45% in circuit analysis and outperforms specialized methods by 41.96--51.84%. Moreover, AutoVSR surpasses closed-source state-of-the-art VLMs in inference cost and computational efficiency. Code is available at https://anonymous.4open.science/r/icml34410/.

Social Aspects · Alignment

Tuan Nguyen, Long Tran-Thanh

Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment. Existing alignment approaches operate primarily during training, such as through fine-tuning or reinforcement learning from human feedback, but these methods are costly and inflexible, requiring retraining whenever new requirements arise. Recent efforts toward inference-time alignment mitigate some of these limitations but still assume access to model internals, which is impractical, and not suitable for third party stakeholders who do not have access to the models. In this work, we propose a model-independent, black-box framework for safety alignment that does not require retraining or access to the underlying LLM architecture. As a proof of concept, we address the problem of trading off between generating safe but uninformative answers versus helpful yet potentially risky ones. We formulate this dilemma as a two-player zero-sum game whose minimax equilibrium captures the optimal balance between safety and helpfulness. LLM agents operationalize this framework by leveraging a linear programming solver at inference time to compute equilibrium strategies. Our results demonstrate the feasibility of black-box safety alignment, offering a scalable and accessible pathway for stakeholders, including smaller organizations and entities in resource-constrained settings, to enforce safety across rapidly evolving LLM ecosystems.

Deep Learning · Generative Models and Autoencoders

Jeongwoo Shin, Jinhwan Sul, Joonseok Lee, Jaewoong Choi, Jaemoo Choi

Diffusion models often yield highly curved trajectories and noisy score targets due to an uninformative, memoryless forward process that induces independent data-noise coupling. We propose Adjoint Schrödinger Bridge Matching (ASBM), a generative modeling framework that recovers optimal trajectories in high dimensions via two stages. First, we view the Schrödinger Bridge (SB) forward dynamic as a coupling construction problem and learn it through a data-to-energy sampling perspective that transports data to an energy-defined prior. Then, we learn the backward generative dynamic with a simple matching loss supervised by the induced optimal coupling. By operating in a non-memoryless regime, ASBM produces significantly straighter and more efficient sampling paths. Compared to prior works, ASBM scales to high-dimensional data with notably improved stability and efficiency. Extensive experiments on image generation show that ASBM improves fidelity with fewer sampling steps. We further showcase the effectiveness of our optimal trajectory via distillation to a one-step generator.

Applications · Time Series

Shiyan Hu, Tengxue Zhang, Jianxin Jin, Xiangfei Qiu, Bin Yang, Chenjuan Guo

Multivariate time series anomaly detection remains challenging as it requires the joint modeling of variable relationships and temporal dependencies. Existing methods often struggle to balance channel relationship modeling and overlook the relative importance of different variables within multivariate time series. To address this, we propose TeamWork, an asymmetric role-aware channel modeling framework that decouples variables into dominant and auxiliary roles according to their contributions to uncertainty reduction. Dominant variables drive system evolution and their deviations more strongly disrupt normal patterns, while auxiliary variables provide complementary cues. These variables with different roles are integrated through a role-aware gated interaction module. Moreover, point and subsequence anomalies can exist in multiple periodic systems, and the same anomaly type may behave differently across short- and long-period series. To capture such variations, we introduce a period-aware masked modeling mechanism. It employs multiple specialized masking mechanisms spanning short to long periods to facilitate comprehensive temporal dependency learning. Extensive experiments on multiple real-world datasets demonstrate that TeamWork achieves superior performance compared with state-of-the-art methods.

Social Aspects · Safety

Zheng Hui, Doni Bloomfield, Noam Kolt

Large language model (LLM) agents increasingly perform commercial tasks that involve retrieving external content such as images and, where appropriate, reproducing that content. LLM agents should comply with the law, including the laws of copyright. Yet today we lack adequate tools to assess whether they do so. To that end, we introduce Copyright-Bench, a benchmark designed to evaluate copyright law compliance of LLM agents. Copyright-Bench is comprised of realistic commercial tasks---website development, merchandise design, and corporate content production---that involve agents selecting between freely licensed content (the use of which is legal) and copyrighted content (the use of which is illegal at least in this setting). Notably, the evaluation introduces prompt variations that simulate different levels of user intent and time pressure. Comparing state-of-the-art agents against a human baseline, we find that: (1) LLM agents take actions that violate copyright law despite the availability of lawful alternatives; and (2) violation rates increase in response to user intent and under simulated time pressure.

General Machine Learning · Transfer, Multitask and Meta-learning

Lotta Mäkinen, Jorge Loria, Samuel Kaski

Meta-learning methods perform well on new within-distribution tasks but often fail when adapting to out-of-distribution target tasks, where transfer from source tasks can induce negative transfer. We propose a causally-aware Bayesian meta-learning method, by conditioning task-specific priors on precomputed latent causal task embeddings, enabling transfer based on mechanistic similarity rather than spurious correlations. Our approach explicitly considers realistic deployment settings where access to target-task data is limited, and adaptation relies on noisy (expert-provided) pairwise judgments of causal similarity between source and target tasks. We provide a theoretical analysis showing that conditioning on causal embeddings controls prior mismatch and mitigates negative transfer under task shift. Empirically, we demonstrate reductions in negative transfer and improved out-of-distribution adaptation in both controlled simulations and a large-scale real-world clinical prediction setting for cross-disease transfer, where causal embeddings align with underlying clinical mechanisms.