Large language models (LLMs) have demonstrated remarkable capability in function-level code generation tasks. Unlike isolated functions, real-world applications demand reasoning over the entire software system: developers must orchestrate how different components interact, maintain consistency across states over time, and ensure the application behaves correctly within the lifecycle and framework constraints. Yet, no existing benchmark adequately evaluates whether LLMs can bridge this gap and construct entire software systems from scratch. To address this gap, we propose \tool, a benchmark consisting of 101 software development problems drawn from real-world Android apps. Given a natural language specification detailing the app functionality, a language model is tasked with \textbf{implementing the functionality into an Android app from scratch}. Developing an Android app from scratch requires understanding and coordinating app states, lifecycle management, and asynchronous operations, calling for LLMs to generate context-aware, robust, and maintainable code. To construct \tool, we design a multi-agent system to automatically summarize the main functionalities from app documents and navigate the app to synthesize test cases validating the functional correctness of app implementation. Following rigorous manual verification by Android development experts, \tool incorporates the test cases within an automated evaluation framework that enables reproducible assessment without human intervention, making it easily adoptable for future research. Our evaluation on 12 flagship LLMs show that all evaluated models achieve low effectiveness, with the best-performing model (GPT-5) developing only 18.8\% functionally correct applications, highlighting fundamental limitations in current models' ability to handle complex, multi-component software engineering challenges.
论文检索
输入标题、作者或关键词，从 12,113 篇学术成果中精准定位
The Distribution Matching Distillation (DMD) has been successfully applied to text-to-image diffusion models such as Stable Diffusion (SD) 1.5. However, vanilla DMD suffers from convergence difficulties on large-scale flow-based text-to-image models, such as SD 3.5 and FLUX. In this paper, we first analyze the issues when applying vanilla DMD on large-scale models. Then, to overcome the scalability challenge, we propose implicit distribution alignment (IDA) to constrain the divergence between the generator and the fake distribution. Furthermore, we propose intra-segment guidance (ISG) to relocate the timestep denoising importance from the teacher model. With IDA alone, DMD converges for SD 3.5; employing both IDA and ISG, DMD converges for SD 3.5 and FLUX.1 dev. Together with a scaled VFM-based discriminator, our final model, dubbed **SenseFlow**, achieves superior performance in distillation for both diffusion based text-to-image models such as SDXL, and flow-matching models such as SD 3.5 Large and FLUX.1 dev. The source code is available at https://github.com/XingtongGe/SenseFlow.
While reinforcement learning (RL) can empower autonomous agents by enabling self-improvement through interaction, its practical adoption remains challenging due to costly rollouts, limited task diversity, unreliable reward signals, and infrastructure complexity, all of which obstruct the collection of scalable experience data. To address these challenges, we introduce DreamGym, the first unified framework designed to synthesize diverse experiences with scalability in mind to enable effective online RL training for autonomous agents. Rather than relying on expensive real-environment rollouts, DreamGym distills environment dynamics into a reasoning-based experience model that derives consistent state transitions and feedback signals through step-by-step reasoning, enabling scalable agent rollout collection for RL. To improve the stability and quality of transitions, DreamGym leverages an experience replay buffer initialized with offline real-world data and continuously enriched with fresh interactions to actively support agent training. To improve knowledge acquisition, DreamGym adaptively generates new tasks that challenge the current agent policy, enabling more effective online curriculum learning. Experiments across diverse environments and agent backbones demonstrate that DreamGym substantially improves RL training, both in fully synthetic settings and in sim-to-real transfer scenarios. On non-RL-ready tasks like WebArena, DreamGym outperforms all baselines by over 30%. And in RL-ready but costly settings, it matches GRPO and PPO performance using only synthetic interactions. When transferring a policy trained purely on synthetic experiences to real-environment RL, DreamGym yields significant additional performance gains while requiring far fewer real-world interactions, providing a scalable warm-start strategy for general-purpose RL.
The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create a emergent need for accurate benchmarking. There are two major gaps in existing benchmarks: (i) the lack of standardized, process-aware evaluation that captures instruction adherence and process fidelity, and (ii) the scarcity of accurately labeled training data. To bridge these gaps, we introduce DARE-bench, a benchmark designed for machine learning modeling and data science instruction following. Unlike many existing benchmarks that rely on human- or model-based judges, all tasks in DARE-bench have verifiable ground truth, ensuring objective and reproducible evaluation. To cover a broad range of tasks and support agentic tools, DARE-bench consists of 6,300 Kaggle-derived tasks and provides both large-scale training data and evaluation sets. Extensive evaluations show that even highly capable models such as gpt-o4-mini struggle to achieve good performance, especially in machine learning modeling tasks. Using DARE-bench training tasks for fine-tuning can substantially improve model performance. For example, supervised fine-tuning boosts Qwen3-32B’s accuracy by 1.83× and reinforcement learning boosts Qwen3-4B’s accuracy by more than 8×. These significant improvements verify the importance of DARE-bench both as an accurate evaluation benchmark and critical training data.
Scaling imitation learning to high-DoF whole-body robots is fundamentally constrained by the scarcity of expert demonstrations. In contrast, large amounts of suboptimal data are readily available and offer a practical way to alleviate supervision bottlenecks in real-world whole-body control. However, leveraging such data introduces two central challenges: how to extract informative signals from imperfect trajectories, and how to cope with the increased learning complexity induced by high-dimensional control. To overcome this, we propose **HVD** (Hierarchical Value-Decomposed Offline Reinforcement Learning). The offline RL formulation provides principled data selection over suboptimal datasets, enabling the policy to prioritize high-value behaviors while down-weighting harmful ones. Complementarily, hierarchical value decomposition organizes learning along the robot’s kinematic structure, improving credit assignment and reducing learning complexity in high-DoF systems. Built on a Transformer-based architecture, HVD supports *multi-modal* and *multi-task* learning, allowing flexible integration of diverse sensory inputs. To enable realistic evaluation and training, we further introduce **WB-50**, a 50-hour dataset of teleoperated and policy rollout trajectories annotated with rewards and preserving natural imperfections, including partial successes, corrections, and failures. Experiments show HVD significantly outperforms existing baselines in success rate across complex whole-body tasks. Our results suggest effective policy learning for high-DoF systems can emerge not from perfect demonstrations, but from structured learning over realistic, imperfect data. Our code is available at https://github.com/LAMDA-RL/HVD.
Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance model performance in perception and reasoning tasks. However, to the best of our knowledge, no open-source work currently offers a feature set as rich as proprietary models (OpenAI O3), which can perform diverse image manipulations and simultaneously enhance logical reasoning capabilities through code. In this paper, we make a preliminary attempt in this direction by introducing \textbf{Thyme} (\textbf{Th}ink Be\textbf{y}ond I\textbf{m}ag\textbf{e}s), a novel paradigm for enabling multimodal large language models to transcend existing ``think with images'' approaches by autonomously generating and executing diverse image processing and computational operations via executable code (Figure 2). This approach not only facilitates a rich, on-the-fly set of image manipulations (e.g., cropping, rotation, contrast enhancement), but also allows for mathematical computations, all while maintaining high autonomy in deciding when and how to apply these operations. We activate this capability through a two-stage training strategy: an initial Supervised Fine-Tuning (SFT) on a curated dataset of 500K samples to teach code generation, followed by a Reinforcement Learning (RL) phase to refine decision-making. For the RL stage, we manually collect and design high-resolution question-answer pairs to increase the learning difficulty, and we propose \textbf{GRPO-ATS} (Group Relative Policy Optimization with Adaptive Temperature Sampling), an algorithm that applies distinct temperatures to text and code generation to balance reasoning exploration with code execution precision. We conduct extensive experimental analysis and ablation studies. As shown in Figure 1, comprehensive evaluations on nearly 20 benchmarks show that Thyme yields significant and consistent performance gains, particularly in challenging high-resolution perception and complex reasoning tasks.
Applications · Everything Else
Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains. However, current benchmarks for evaluating MLLMs primarily emphasize general knowledge and vertical step-by-step reasoning typical of STEM disciplines, while overlooking the distinct needs and potential of the Humanities and Social Sciences (HSS). Tasks in the HSS domain require more horizontal, interdisciplinary thinking and a deep integration of knowledge across related fields, which presents unique challenges for MLLMs, particularly in linking abstract concepts with corresponding visual representations. Addressing this gap, we present HSSBench, a dedicated benchmark designed to assess the capabilities of MLLMs on HSS tasks in multiple languages, including the six official languages of the United Nations. We also introduce a novel data generation pipeline tailored for HSS scenarios, in which multiple domain experts and automated agents collaborate to generate and iteratively refine each sample. HSSBench contains over 13,000 meticulously designed samples, covering six key categories. We benchmark more than 20 mainstream MLLMs on HSSBench and demonstrate that it poses significant challenges even for state-of-the-art models. We hope that this benchmark will inspire further research into enhancing the cross-disciplinary reasoning abilities of MLLMs, especially their capacity to internalize and connect knowledge across fields.
Audio is a fundamental modality for analyzing speech, music, and environmental sounds. While pretrained audio models have significantly advanced audio understanding, they remain fragile in real-world scenarios where data distributions evolve over time. In this work, we present the first systematic benchmark for audio continual learning (CL) with pretrained models (PTMs) and provide a comprehensive analysis of its unique challenges. Unlike in the vision domain where parameter-efficient fine-tuning (PEFT) has proven effective for CL, directly applying such strategies to audio leads to poor performance. This is due to a fundamental property of audio backbones: they emphasize low-level spectral details rather than structured semantics, resulting in severe upstream–downstream misalignment. Through extensive empirical analysis, we identify a promising technical route based on analytic classifiers with first-session adaptation (FSA), but also uncover two major limitations: representation saturation in coarse-grained scenarios and representation shifts in fine-grained scenarios. To address these challenges, we propose **PACE**, an innovative method that improves FSA via a regularized analytic classifier and introduces multi-session adaptation through adaptive subspace-orthogonal PEFT for better semantic alignment. Additionally, we design spectrogram-based boundary-aware perturbations to mitigate representation overlap and improve stability. Experiments across six diverse audio CL benchmarks demonstrate that PACE substantially outperforms state-of-the-art baselines, representing a significant step toward robust and scalable audio CL with PTMs.
Despite improvements by length extrapolation, efficient attention and memory modules, handling infinitely long documents without performance degradation during extrapolation remains the ultimate challenge in long-text processing. To solve this problem, We introduce a novel agent workflow, \method, which processes text in segments and updates memory through an overwrite strategy, addressing the challenge of long-context task through enhanced memory management. We further extend the DAPO algorithm to directly optimize memory ability in an end-to-end fashion, facilitating training via independent-context multi-conversation generation. Experimental results demonstrate that MemAgent has superb long-context capabilities, being able to extrapolate from an 8K context to a 3.5M QA task with a performance loss of less than 10\% and achieving over 95\% on the 512K NIAH test.
Large reasoning models (LRMs) trained with *Reinforcement Learning with Verifiable Rewards* (RLVR) have achieved remarkable progress on complex reasoning tasks. However, RLVR heavily relies on on-policy rollout generation, whose cost grows rapidly with rollout length and model size, eventually becoming the training bottleneck. Our empirical analysis reveals that independent rollouts for the same query often share similar early steps, indicating substantial redundancy. To address this, we propose **Pros** (**P**refix **R**euse for **O**n-policy **S**ampling), a paradigm that reuses promising prefixes of historical rollouts in RLVR training. **Pros** appends these self-generated partial rollouts to the original queries to form *Augmented Queries*, which are then used as regular training inputs in subsequent iterations, thereby reducing redundant computation. To select training batch from augmented queries, **Pros** adopts a hierarchical Bayesian model to estimate their pass rates and prioritize those with the highest reward uncertainty. Experiments across diverse settings show that **Pros** consistently improves training efficiency and achieves higher accuracy than strong baselines. These results highlight **Pros** as a practical path toward scalable and compute-efficient RLVR.
Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences on a Likert scale (e.g., significantly better, better, slightly better, negligibly better), existing methods typically apply ad-hoc heuristics, such as margin terms or scaling factors, to loss functions derived from binary preference models like Bradley-Terry. These approaches lack an underlying mathematical model for how ordinal preference data is generated. We present a theoretically grounded framework that formulates reward modeling with Likert scale preferences as a discrete ordinal regression problem. We derive two loss functions from this formulation: a negative log-likelihood loss and an all-threshold loss, both of which learn threshold parameters that naturally capture the ordinal structure of preferences. Unlike existing heuristic methods that manually specify fixed margins or scaling weights, our approach learns these parameters directly from data within a coherent probabilistic framework. Experimental results on multiple benchmarks demonstrate that our ordinal regression approach consistently achieves competitive or superior performance compared to existing heuristic methods across diverse evaluation categories including chat, reasoning, and safety tasks. Our work provides the first principled mathematical framework for incorporating Likert scale preferences into reward model training, moving beyond ad-hoc modifications of binary preference models to enable more effective utilization of fine-grained human feedback.
Spiking Neural Networks (SNNs) represent a promising paradigm for energy-efficient neuromorphic computing due to their bio-plausible and spike-driven characteristics. However, the robustness of SNNs in complex adversarial environments remains significantly constrained. In this study, we theoretically demonstrate that those threshold-neighboring spiking neurons are the key factors limiting the robustness of directly trained SNNs. We find that these neurons set the upper limits for the maximum potential strength of adversarial attacks and are prone to state-flipping under minor disturbances. To address this challenge, we propose a Threshold Guarding Optimization (TGO) method, which comprises two key aspects. First, we incorporate additional constraints into the loss function to move neurons' membrane potentials away from their thresholds. It increases SNNs' gradient sparsity, thereby reducing the theoretical upper bound of adversarial attacks. Second, we introduce noisy spiking neurons to transition the neuronal firing mechanism from deterministic to probabilistic, decreasing their state-flipping probability due to minor disturbances. Extensive experiments conducted in standard adversarial scenarios prove that our method significantly enhances the robustness of directly trained SNNs. These findings pave the way for advancing more reliable and secure neuromorphic computing in real-world applications.
Network alignment (NA) aims to identify node correspondence across different networks and serves as a critical cornerstone behind various downstream multi-network learning tasks. Despite growing research in NA, there lacks a comprehensive library that facilitates the systematic development and benchmarking of NA methods. In this work, we introduce PLANETALIGN, a comprehensive Python library for network alignment that features a rich collection of built-in datasets, methods, and evaluation pipelines with easy-to-use APIs. Specifically, PLANETALIGN integrates 18 datasets and 14 NA methods with extensible APIs for easy use and development of NA methods. Our standardized evaluation pipeline encompasses a wide range of metrics, enabling a systematic assessment of the effectiveness, scalability, and robustness of NA methods. Through extensive comparative studies, we reveal practical insights into the strengths and limitations of existing NA methods. We hope that PLANETALIGN can foster a deeper understanding of the NA problem and facilitate the development and benchmarking of more effective, scalable, and robust methods in the future. The source code of PLANETALIGN is available at https://github.com/yq-leo/PlanetAlign
While diffusion models have achieved remarkable performance in image generation, they often struggle with the imbalanced datasets frequently encountered in real-world applications, resulting in significant performance degradation on minority classes. In this paper, we identify model capacity allocation as a key and previously underexplored factor contributing to this issue, providing a perspective that is orthogonal to existing research. Our empirical experiments and theoretical analysis reveal that majority classes monopolize an unnecessarily large portion of the model's capacity, thereby restricting the representation of minority classes. To address this, we propose Capacity Manipulation (CM), which explicitly reserves model capacity for minority classes. Our approach leverages a low-rank decomposition of model parameters and introduces a capacity manipulation loss to allocate appropriate capacity for capturing minority knowledge, thus enhancing minority class representation. Extensive experiments demonstrate that CM consistently and significantly improves the robustness of diffusion models on imbalanced datasets, and when combined with existing methods, further boosts overall performance.
Bayesian optimization (BO) is a powerful approach for black-box optimization, and in many real-world problems, domain experts possess valuable prior knowledge about promising regions of the search space. However, existing prior-informed BO methods are often overly complex, tied to specific acquisition functions, or highly sensitive to inaccurate priors. We propose DynMeanBO, a simple and general framework that incorporates expert priors into the Gaussian process mean function with a dynamic decay mechanism. This design allows BO to exploit expert knowledge in the early stages while gradually reverting to standard BO behavior, ensuring robustness against misleading priors while retaining the exploratory behavior of standard BO. DynMeanBO is broadly compatible with acquisition functions, introduces negligible computational cost, and comes with convergence guarantees under Expected Improvement and Upper Confidence Bound. Experiments on synthetic benchmarks and hyperparameter optimization tasks show that DynMeanBO accelerates convergence with informative priors and remains robust under biased ones.
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by incorporating external knowledge bases, but this may expose them to extraction attacks, leading to potential copyright and privacy risks. However, existing extraction methods typically rely on malicious inputs such as prompt injection or jailbreaking, making them easily detectable via input- or output-level detection. In this paper, we introduce **I**mplicit **K**nowledge **E**xtraction **A**ttack (**IKEA**), which conducts *Knowledge Extraction* on RAG systems through benign queries. Specifically, **IKEA** first leverages anchor concepts—keywords related to internal knowledge—to generate queries with a natural appearance, and then designs two mechanisms that lead anchor concepts to thoroughly "explore" the RAG's knowledge: (1) Experience Reflection Sampling, which samples anchor concepts based on past query-response histories, ensuring their relevance to the topic; (2) Trust Region Directed Mutation, which iteratively mutates anchor concepts under similarity constraints to further exploit the embedding space. Extensive experiments demonstrate **IKEA**'s effectiveness under various defenses, surpassing baselines by over 80% in extraction efficiency and 90\% in attack success rate. Moreover, the substitute RAG system built from **IKEA**'s extractions shows close performance to the original RAG and outperforms those based on baselines across multiple evaluation tasks, underscoring the stealthy copyright infringement risk in RAG systems.
Applications · Neuroscience, Cognitive Science
Spiking Neural Networks (SNNs) are regarded as energy-efficient neural architectures due to their event-driven, spike-based computation paradigm. However, existing SNNs suffer from two fundamental limitations: (1) the constrained representational space imposed by binary spike firing mechanisms, which restricts the network's capacity to encode complex spatiotemporal patterns, and (2) the ineffective design of surrogate gradient functions that leads to gradient mismatch issues and suboptimal learning dynamics. To address these challenges, we propose the Parametric Invertible Transformation (PIT), which operates in a conjugate manner with neuronal dynamics to achieve adaptive modulation and augmented spike representations simultaneously. Second, we design an auxiliary gradient correction term to mitigate the gradient mismatch issue and oscillation phenomena during training. Moreover, we introduce a theoretical framework for analyzing the spatiotemporal representation space of SNNs. Extensive experiments on both static and neuromorphic datasets demonstrate state-of-the-art performance with our proposed method. This approach lays the theoretical foundation for expanding the spatiotemporal representations of SNNs, offering a viable pathway for developing low-latency and high-performance neuromorphic processing systems in resource-constrained environments. The code is available at https://github.com/YinsongYan/ICLR26.
Long video generation with Diffusion Transformers (DiTs) is bottlenecked by the quadratic scaling of full attention with sequence length. Since attention is highly redundant, outputs are dominated by a small subset of query–key pairs. Existing sparse methods rely on blockwise coarse estimation, whose accuracy–efficiency trade-offs are constrained by block size. This paper introduces Mixture-of-Groups Attention (MoGA), an efficient sparse attention that uses a lightweight, learnable token router to precisely match tokens without blockwise estimation. Through semantic-aware routing, MoGA enables effective long-range interactions. As a kernel-free method, MoGA integrates seamlessly with modern attention stacks, including FlashAttention and sequence parallelism. Building on MoGA, we develop an efficient long video generation model that end-to-end produces minute-level, multi-shot, 480p videos at 24 fps, with a context length of approximately 580k. Comprehensive experiments on various video generation tasks validate the effectiveness of our approach. Project website: https://jiawn-creator.github.io/mixture-of-groups-attention/ .
Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective---reconstructing clean signals from corrupted inputs, such as signals degraded by Gaussian noise or masking---a process we term \emph{denoising}. Motivated by this insight, we propose aligning tokenizer embeddings directly with the downstream denoising objective, encouraging latent embeddings that remain reconstructable even under significant corruption. To achieve this, we introduce the Latent Denoising Tokenizer (\method), a simple yet highly effective tokenizer trained to reconstruct clean images from latent embeddings corrupted via interpolative noise or random masking. Extensive experiments on class-conditioned (ImageNet $256\times256$ and $512\times512$) and text-conditioned (MSCOCO) image generation benchmarks demonstrate that our \method consistently improves generation quality across \textit{six} representative generative models compared to prior tokenizers. Our findings highlight denoising as a fundamental design principle for tokenizer development, and we hope it could motivate new perspectives for future tokenizer design. Code is available at: https://github.com/Jiawei-Yang/DeTok
Machine learning promises to revolutionize drug discovery, but its "black-box" nature and narrow focus limit adoption by experts. While Large Language Models (LLMs) offer a path forward with their broad knowledge and interactivity, existing methods remain data-intensive and lack transparent reasoning. To address these issues, we present DrugTrail, an LLM-based framework for explainable drug discovery that integrates structured reasoning trajectories with a Druggability‑Tailored Preference Optimization (DTPO) strategy. It not only introduces structured reasoning traces to articulate the "how" and "why" behind its conclusions but also serve to guide task-specific reasoning pathways within the LLM's vast knowledge space, thereby enhancing its interpretability and reliability of its final outputs. Furthermore, based on the fact that optimizing for binding affinity alone does not equate to optimizing for druggability, DTPO explicitly moves beyond single-metric optimization and opens up a broader search space that balances affinity with other essential factors. Extensive experiments demonstrate the effectiveness of our approach and its generalizability to a wider range of biomolecular optimization domains, bridging the gap between LLM reasoning capabilities and trustworthy AI-assisted drug discovery.