The evaluation of code-generating Large Language Models (LLMs) is fundamentally constrained by two intertwined challenges: a reliance on static, easily contaminated problem sources and the use of superficial, low-rigor testing. This paper introduces a new benchmark construction philosophy, Dual Scaling, designed to systematically address both limitations. Our approach involves continuously scaling the source of problems from dynamic, real-world code repositories and systematically scaling the rigor of tests via automated, high-coverage Property-Based Testing (PBT). We instantiate this philosophy in CODE2BENCH, an end-to-end framework that leverages Scope Graph analysis for principled dependency classification and a 100% branch coverage quality gate to ensure test suite integrity. Using this framework, we construct CODE2BENCH-2509, a new benchmark suite with native instances in both Python and Java. Our extensive evaluation of 10 state-of-the-art LLMs on CODE2BENCH-2509, powered by a novel "diagnostic fingerprint" visualization, yields three key insights: (1) models exhibit a fundamental performance gap, excelling at API application (Weakly Self-Contained tasks) but struggling with algorithmic synthesis (Self-Contained tasks); (2) a model’s performance is profoundly shaped by the target language’s ecosystem, a nuance we are the first to systematically quantify; and (3) our rigorous, scaled testing is critical in uncovering an "illusion of correctness" prevalent in simpler benchmarks. Our work presents a robust, scalable, and diagnostic paradigm for the next generation of LLM evaluation in software engineering. The code, data, and results are available at https://code2bench.github.io/.
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
With the rapid development of foundation video generation technologies, long video generation models have exhibited promising research potential thanks to expanded content creation space. Recent studies reveal that the goal of long video generation tasks is not only to extend video duration but also to accurately express richer narrative content within longer videos. However, due to the lack of evaluation benchmarks specifically designed for long video generation models, the current assessment of these models primarily relies on benchmarks with simple narrative prompts (e.g., VBench). To the best of our knowledge, our proposed NarrLV is the first benchmark to comprehensively evaluate the Narrative expression capabilities of Long Video generation models. Inspired by film narrative theory, (i) we first introduce the basic narrative unit maintaining continuous visual presentation in videos as Temporal Narrative Atom (TNA), and use its count to quantitatively measure narrative richness. Guided by three key film narrative elements influencing TNA changes, we construct an automatic prompt generation pipeline capable of producing evaluation prompts with a flexibly expandable number of TNAs. (ii) Then, based on the three progressive levels of narrative content expression, we design an effective evaluation metric using the MLLM-based question generation and answering framework. (iii) Finally, we conduct extensive evaluations on existing long video generation models and the foundation generation models that underpin them. Experimental results demonstrate that our metric aligns closely with human judgments. The derived evaluation outcomes reveal the detailed capability boundaries of current video generation models in narrative content expression.
Computer Vision · 3D Rendering & Reconstruction
Part-based 3D generation holds great potential for various applications. Previous part generators that represent parts using implicit vector-set tokens often suffer from insufficient geometric details. Another line of work adopts an explicit voxel representation but shares a global voxel grid among all parts; this often causes small parts to occupy too few voxels, leading to degraded quality. In this paper, we propose \textit{FullPart}, a novel framework that combines both implicit and explicit paradigms. It first derives the bounding box layout through an implicit box vector-set diffusion process, a task that implicit diffusion handles effectively since box tokens contain little geometric detail. Then, it generates detailed parts, each within its own fixed full-resolution voxel grid. Instead of sharing a global low-resolution space, each part in our method—even small ones—is generated at full resolution, enabling the synthesis of intricate details. We further introduce a center-point encoding strategy to address the misalignment issue when exchanging information between parts of different actual sizes, thereby maintaining global coherence. Moreover, to tackle the scarcity of reliable part data, we present \textit{PartVerse-XL}, the largest human-annotated 3D part dataset to date with 40K objects and 320K parts. Extensive experiments demonstrate that FullPart achieves state-of-the-art results in 3D part generation. Code, model, and dataset are available at https://fullpart3d.github.io.
Applications · Language, Speech and Dialog
The pursuit of human-like conversational agents has long been guided by the Turing test. For modern speech-to-speech (S2S) systems, a critical yet unanswered question is whether they can converse like humans. To tackle this, we conduct the first Turing test for S2S systems, collecting 2,968 human judgments on dialogues between 9 state-of-the-art S2S systems and 28 human participants. Our results deliver a clear finding: no existing evaluated S2S system passes the test, revealing a significant gap in human-likeness. To diagnose this failure, we develop a fine-grained taxonomy of 18 human-likeness dimensions and crowd-annotate our collected dialogues accordingly. Our analysis shows that the bottleneck is not semantic understanding but stems from paralinguistic features, emotional expressivity, and conversational persona. Furthermore, we find that off-the-shelf AI models perform unreliably as Turing test judges. In response, we propose an interpretable model that leverages the fine-grained human-likeness ratings and delivers accurate and transparent human-vs-machine discrimination, offering a powerful tool for automatic human-likeness evaluation. Our work establishes the first human-likeness evaluation for S2S systems and moves beyond binary outcomes to enable detailed diagnostic insights, paving the way for human-like improvements in conversational AI systems.
Computer Vision · Vision Models & Multimodal
Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like processing paradigms, overlooking the spatiotemporal sparsity of event streams and resulting in high computational cost. In this paper, we propose EventFlash, the first efficient MLLM to explore spatiotemporal token sparsification for reducing data redundancy and accelerating inference. Technically, we first build EventMind, a large-scale and scene-diverse dataset with over 500k instruction sets, providing both short and long event stream sequences to support our curriculum training strategy. Then, we present the adaptive temporal window aggregation module for efficient temporal sampling, which adaptively compresses temporal tokens while retaining key temporal cues. Finally, the sparse density-guided attention module is designed to improve spatial token efficiency by selecting informative regions and suppressing empty or sparse areas. Experimental results show that EventFlash achieves a 12.4x throughput improvement over the baseline (EventFlash-Zero) while maintaining comparable performance. It supports long-range event stream processing with up to 1,000 bins, significantly outperforming EventGPT’s 5-bin limit. We believe EventFlash serves as an efficient foundation model for event-based vision.
Leading language model (LM) providers like OpenAI and Anthopic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting, we make three contributions: First, while past work has shown that safety alignment is superficial, we correspondingly demonstrate that existing fine-tuning attacks are "shallow" -- attacks target only the first several tokens of the model response, and consequently can be blocked by generating the first several response tokens with an aligned model. Second, we conceptually illustrate how to make attacks deeper by introducing a new fine-tuning attack that trains models to first refuse harmful requests before answering them; this ``refuse-then-comply" strategy bypasses shallow defenses and produces harmful responses that evade output filters. Third, we demonstrate the potency of our new fine-tuning attack by jailbreaking both open-source models equipped with defenses and production models, achieving attack success rates of 57% and 72% against GPT-4o and Claude Haiku, respectively. Our attack received a $2000 bug bounty from OpenAI and was acknowledged as a vulnerability by Anthropic.
Reinforcement Learning · Deep RL
Reinforcement learning (RL) for LLM reasoning has rapidly emerged as a prominent research area, marked by a significant surge in related studies on both algorithmic innovations and practical applications. Despite this progress, several critical challenges remain, including the absence of standardized guidelines for applying RL techniques and a fragmented understanding of their underlying mechanisms. In addition, inconsistent experimental settings, variations in training data, and differences in model initialization have led to conflicting conclusions, obscuring the key characteristics of these techniques and creating confusion among practitioners when selecting appropriate techniques. This paper systematically reviews widely adopted RL techniques through rigorous reproductions and isolated evaluations within a unified open-source framework. We analyze the internal mechanisms, applicable scenarios, and core principles of each technique through fine-grained experiments, including datasets of varying difficulty, model sizes, and architectures. Based on these insights, we present clear guidelines for selecting RL techniques tailored to specific setups and provide a reliable roadmap for practitioners navigating the RL for the LLM domain. Finally, we show that a minimalist combination of two techniques can unlock the learning capability of critic-free policies with a vanilla PPO loss. The results demonstrate that our simple combination consistently improves performance, surpassing strategies such as GRPO and DAPO.
Social Aspects · Trustworthy Machine Learning
We introduce MUSE, a novel watermarking paradigm for tabular generative models. Existing approaches often exploit DDIM invertibility to watermark tabular diffusion models, but tabular diffusion models suffer from poor invertibility, leading to degraded performance. To overcome this limitation, we leverage the computational efficiency of tabular generative models and propose a multi-sample selection paradigm, where watermarks are embedded by generating multiple candidate samples and selecting one according to a specialized scoring function. The key advantages of MUSE include (1) Model-agnostic: compatible with any tabular generative model that supports repeated sampling; (2) Flexible: offers flexible designs to navigate the trade-off between generation quality, detectability, and robustness; (3) Calibratable: theoretical analysis provides principled calibration of watermarking strength, ensuring minimal distortion to the original data distribution. Extensive experiments on five datasets demonstrate that MUSE substantially outperforms existing methods. Notably, it reduces the distortion rates by 84-88% for fidelity metrics compared with the best performing baselines, while achieving 1.0 TPR@0.1%FPR detection rate.
The Transformer architecture, despite its widespread success, struggles with long-context scenarios due to quadratic computation and linear memory growth. While various linear attention variants mitigate these efficiency constraints by compressing context into fixed-size states, they often degrade performance in tasks such as in-context retrieval and reasoning. To address this limitation and achieve more effective context compression, we propose two key innovations. First, we introduce a row-sparse update formulation for linear attention by conceptualizing state updating as information categorization. This enables sparse state updates via softmax-based top-$k$ row selection, thereby extending receptive fields and reducing information interference. Second, we present Sparse State Expansion (SSE) within the sparse framework, which expands the contextual state into multiple partitions, effectively decoupling parameter size from state capacity while maintaining the sparse row-selection paradigm. Supported by efficient parallelized implementations, our design achieves highly discriminative state representations. We extensively validate SSE in both pure linear and hybrid (SSE-H) architectures across language modeling, in-context retrieval, and mathematical reasoning benchmarks. SSE demonstrates strong retrieval performance and scales favorably with state size. Moreover, after reinforcement learning (RL) training, our 2B SSE-H model achieves state-of-the-art mathematical reasoning performance among small reasoning models, scoring 64.5 on AIME24 and 50.2 on AIME25, significantly outperforming similarly sized open-source Transformers. These results highlight SSE as a promising and efficient architecture for long-context modeling.
Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inference. However, effectively training large diffusion policies using reinforcement learning (RL) remains challenging. Existing methods either suffer from unstable training due to directly maximizing value objectives, or face computational issues due to relying on crude Gaussian likelihood approximation, which requires a large amount of sufficiently small denoising steps. In this work, we propose DIPOLE (Dichotomous diffusion Policy improvement), a novel RL algorithm designed for stable and controllable diffusion policy optimization. We begin by revisiting the KL-regularized objective in RL, which offers a desirable weighted regression objective for diffusion policy extraction, but often struggles to balance greediness and stability. We then formulate a greedified policy regularization scheme, which naturally enables decomposing the optimal policy into a pair of stably learned dichotomous policies: one aims at reward maximization, and the other focuses on reward minimization. Under such a design, optimized actions can be generated by linearly combining the scores of dichotomous policies during inference, thereby enabling flexible control over the level of greediness.Evaluations in offline and offline-to-online RL settings on ExORL and OGBench demonstrate the effectiveness of our approach. We also use DIPOLE to train a large vision-language-action (VLA) model for end-to-end autonomous driving (AD) and evaluate it on the large-scale real-world AD benchmark NAVSIM, highlighting its potential for complex real-world applications.
Social Aspects · Privacy-preserving Statistics and Machine Learning
Large-scale deep learning models are known to *memorize* parts of the training set. In machine learning theory, memorization is often framed as interpolation or label fitting, and classical results show that this can be achieved when the number of parameters $p$ in the model is larger than the number of training samples $n$. In this work, we consider memorization from the perspective of *data reconstruction*, demonstrating that this can be achieved when $p$ is larger than $dn$, where $d$ is the dimensionality of the data. More specifically, we show that, in the random features model, when $p \gg dn$, the subspace spanned by the training samples in feature space gives sufficient information to identify the individual samples in input space. Our analysis suggests an optimization method to reconstruct the dataset from the model parameters, and we demonstrate that this method performs well on various architectures (random features, two-layer fully-connected and deep residual networks). Our results reveal a *law of data reconstruction*, according to which the entire training dataset can be recovered as $p$ exceeds the threshold $dn$.
General Machine Learning · Representation Learning
Multimodal dataset distillation aims to construct compact synthetic datasets that enable efficient compression and knowledge transfer from large-scale image-text data. However, existing approaches often fail to capture the complex, dynamically evolving knowledge embedded in the later training stages of teacher models. This limitation leads to degraded student performance and compromises the quality of the distilled data. To address critical challenges such as pronounced cross-stage performance gaps and unstable teacher trajectories, we propose Phased Teacher Model with Shortcut Trajectory (PTM-ST)—a novel phased distillation framework. PTM-ST leverages stage-aware teacher modeling and a shortcut-based trajectory construction strategy to accurately fit the teacher’s learning dynamics across distinct training phases. This enhances both the stability and expressiveness of the distillation process. Through theoretical analysis and comprehensive experiments, we show that PTM-ST significantly mitigates optimization oscillations and inter-phase knowledge gaps, while also reducing storage overhead. Our method consistently surpasses state-of-the-art baselines on Flickr30k and COCO, achieving up to 13.5\% absolute improvement and an average gain of 9.53\% on Flickr30k. Code: \url{https://github.com/Previsior/PTM-ST}.
Computer Vision · Everything Else
Salient Object Ranking (SOR) aims to predict human attention shifts across different salient objects in a scene. Although a number of methods have been proposed for the task, they typically rely on modeling the bottom-up influences of image features on attention shifts. In this work, we observe that when free-viewing an image, humans instinctively browse the objects in such a way as to maximize contextual understanding of the image. This implies a cyclical interaction between content (or story) understanding of the image and attention shift over it. Based on this observation, we propose a novel SOR approach that models this explicit top-down cognitive pathway with two novel modules: a story prediction (SP) module and a guided ranking (GR) module. By formulating content understanding as the image caption generation task, the SP module learns to generate and complete the image captions conditioned on the salient object queries of the GR module, while the GR module learns to detect salient objects and their viewing orders guided by the SP module. Extensive experiments on SOR benchmarks demonstrate that our approach outperforms state-of-the-art SOR methods.
Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long context lengths during training, leading to substantial computational costs. While multi-stage training can partially mitigate this, starting with overly short contexts often causes irreversible performance degradation, ultimately failing to reduce overall training compute significantly. In this paper, we introduce **T**hinking-**F**ree **P**olicy **I**nitialization (**TFPI**), a simple yet effective adaptation to RLVR that bridges long Chain-of-Thought (CoT) distillation and standard RLVR. TFPI employs a simple *ThinkFree* operation, explicitly discarding the thinking content via a direct *</think>* append, to reduce token usage during inference. Training with *ThinkFree*-adapted inputs improves performance and lowers token consumption, even in the original slow-thinking mode. Extensive experiments across various benchmarks have shown that {\method} accelerates RL convergence, achieves a higher performance ceiling, and yields more token-efficient reasoning models without specialized rewards or complex training designs. With TFPI only, we train a 4B model to reach 89.0% accuracy on AIME24 and 65.5% on LiveCodeBench using less than 4K H20 hours.
General Machine Learning · Representation Learning
Many state-of-the-art methods in deep learning fail at systematic reasoning in settings which require compositional generalization. To address this, we propose a novel architecture which uses a nonparametric latent space, information-theoretic regularization of this space, and test-time gradient-based search to achieve strong performance on compositional meta-learning tasks such as program induction, Raven's progressive matrices, and linguistic systematicity tasks. Our proposed architecture, Abduction Transformer, uses nonparametric mixture distributions to represent inferred hidden causes of few-shot meta-learning instances. These representations are refined at test-time via gradient descent to better account for the observed few-shot examples, a form of variational posterior inference which allows Abduction Transformer to solve meta-learning tasks that require novel recombinations of knowledge acquired during training. Our method outperforms standard transformer architectures and a contemporary test-time adaptive variational approach, indicating a promising new direction for neural networks capable of systematic generalization.
Learning generative models directly from corrupted observations is a long-standing challenge across natural and scientific domains. We introduce **Restoration Score Distillation (RSD)**, a unified framework for learning high-fidelity, one-step generative models using **only** degraded data of the form $ y = \mathcal{A}(x) + \sigma \varepsilon, x\sim p_X,\ \varepsilon\sim \mathcal{N}(0,I_m), $ where the mapping $\mathcal{A}$ may be the identity or a non-invertible corruption operator (e.g., blur, masking, subsampling, Fourier acquisition). RSD first pretrains a corruption-aware diffusion teacher on the observed measurements, then *distills* it into an efficient one-step generator whose samples are statistically closer to the clean distribution $p_X$. The framework subsumes identity corruption (denoising task) as a special case of our general formulation. Empirically, RSD consistently reduces Fr\'echet Inception Distance (FID) relative to corruption-aware diffusion teachers across noisy generation (CIFAR-10, FFHQ, CelebA-HQ, AFHQ-v2), image restoration (Gaussian deblurring, random inpainting, super-resolution, and mixtures with additive noise), and multi-coil MRI—*without access to any clean images*. The distilled generator inherits one-step sampling efficiency, yielding up to $30\times$ speedups over multi-step diffusion while surpassing the teachers after substantially fewer training iterations. These results establish score distillation as a practical tool for generative modeling from corrupted data, *not merely for acceleration*. We provide theoretical support for the use of distillation in enhancing generation quality in the Appendix. The code is available at https://github.com/TianyuCodings/RSD.
Theory · Interpretability and Visualization
In this paper, we establish a dimension- and precision-independent impossibility result for a simplified transformer model. Due to their size, a comprehensive understanding of the internal operations of frontier large language models (LLMs) is beyond the reach of current methods, but research into small and interpretable models has proven successful. We study the representational limits of attention, the core of transformer models, through the lens of the Endpoint Selection Problem (ESP), a simple yet expressive learning task defined over arcs of a directed graph. Our main theoretical results are twofold: (i) 1-head, 1-layer, attention-only transformers cannot solve ESP on any graph containing a cycle, even with unbounded dimension and precision; but, all DAGs (Directed Acyclic Graph) are solvable with zero error (ii) in contrast, a 2-head, 1-layer, attention-only transformer can solve ESP on arbitrary directed graphs with constant embedding dimension and logarithmic precision. Prior lower bounds were conditional on bounds on dimension and precision. Through a transformation, we extend our impossibility result from ESP to the much studied 2-hop induction head problem. Further, we uncover a surprising connection to NP-completeness by showing that the optimal error of the 1-head transformer is exactly related to the size of MAS (Maximum Acyclic Subgraph) and hence inapproximable. Finally, we validate our theory with experiments and observe that gradient-based optimization can reliably find 1-head solutions for DAGs and 2-head solutions for arbitrary graphs with cycles, whereas 1-head models struggle to reach the optimal solution in graphs with cycles. We believe that our techniques are of independent interest and have the potential to establish a new fine-grained hierarchy of transformer architectures, each with greater problem-solving power than the last.
Applications · Language, Speech and Dialog
As large language models (LLMs) become increasingly integrated into daily life, there is growing demand for AI assistants that are not only reactive but also proactive and personalized. While recent advances have pushed forward proactivity and personalization individually, their combination remains underexplored. To bridge this gap, we introduce ProPerSim, a new task and simulation framework for developing assistants capable of making timely, personalized recommendations in realistic home scenarios. In our simulation environment, a user agent with a rich persona interacts with the assistant, providing ratings on how well each suggestion aligns with its preferences and context. The assistant’s goal is to use these ratings to learn and adapt to achieve higher scores over time. Built on ProPerSim, we propose ProPerAssistant, a retrieval-augmented, preference-aligned assistant that continually learns and adapts through user feedback. Experiments across 32 diverse personas show that ProPerAssistant adapts its strategy and steadily improves user satisfaction, highlighting the promise of uniting proactivity and personalization.
Social Aspects · Fairness, Equity, Justice and Safety
Past work seeks to align large language model (LLM)-based assistants with a target set of values, but such assistants are frequently forced to make tradeoffs *between* values when deployed. In response to the scarcity of value conflict in existing alignment datasets, we introduce ConflictScope, an automatic pipeline to evaluate how LLMs prioritize different values. Given a user-defined value set, ConflictScope automatically generates scenarios in which a language model faces a conflict between two values sampled from the set. It then prompts target models with an LLM-written ``user prompt'' and evaluates their free-text responses to elicit a ranking over values in the value set. Comparing results between multiple-choice and open-ended evaluations, we find that models shift away from supporting protective values, such as harmlessness, and toward supporting personal values, such as user autonomy, in more open-ended value conflict settings. However, including detailed value orderings in models' system prompts improves alignment with a target ranking by 14%, showing that system prompting can achieve moderate success at aligning LLM behavior under value conflict. Our work demonstrates the importance of evaluating value prioritization in models and provides a foundation for future work in this area.
General Machine Learning · Probabilistic Methods
Federated learning (FL) is increasingly adopted in domains like healthcare, where data privacy is paramount. A fundamental challenge in these systems is statistical heterogeneity—the fact that data distributions vary significantly across clients (e.g., different hospitals may treat distinct patient demographics). While current FL algorithms focus on aggregating model updates from these heterogeneous clients, the potential of the central server remains under-explored. This paper is motivated by a healthcare scenario: could a central server not only coordinate model training but also guide a new patient to the hospital best equipped for their specific condition? We generalize this idea to propose a novel paradigm for FL systems where the server actively guides the allocation of new tasks or queries to the most appropriate client. To enable this, we introduce a density ratio model and empirical likelihood-based framework that simultaneously addresses two goals: (1) learning effective local models on each client, and (2) finding the best matching client for a new query. Empirical results demonstrate the framework's effectiveness on benchmark datasets, showing improvements in both model accuracy and the precision of client guidance compared to standard FL approaches. This work opens a new direction for building more intelligent and resource-efficient FL systems that leverage heterogeneity as a feature, not just a bug.