论文检索

Computer Vision · Image and Video Generation

Guozhen Zhang, Haiguang Wang, Chunyu Wang, Yuan Zhou, Qinglin Lu, Limin Wang

Generative Video Frame Interpolation (VFI), which synthesizes intermediate frames from a given pair of start and end frames, plays a pivotal role in video creation. However, existing generative VFI methods are constrained to producing a fixed number of intermediate frames, which significantly limits the flexibility in adjusting the frame rate or duration of videos during the creation process. In this work, we present \textbf{ArbInterp}, a novel generative VFI framework that enables efficient interpolation at any timestamp and of any length. Specifically, to support interpolation at any timestamp, we propose the Timestamp-aware Rotary Position Embedding (TaRoPE), which modulates positions in temporal RoPE to align generated frames with target normalized timestamps. This design enables fine-grained control over frame timestamps, addressing the inflexibility of fixed-position paradigms in prior work. For any-length interpolation, we decompose long-sequence generation into segment-wise frame synthesis. We further design a novel appearance-motion decoupled conditioning strategy: it leverages prior segment endpoints to enforce appearance consistency and temporal semantics to maintain motion coherence, ensuring seamless spatiotemporal transitions across segments. Experimentally, we build comprehensive benchmarks for multi-scale frame interpolation (2× to 32×) to assess generalizability across arbitrary interpolation factors. Results show that ArbInterp outperforms prior methods across all scenarios with higher fidelity and more seamless spatiotemporal continuity. Video demos are provided on the website: https://mcg-nju.github.io/ArbInterp-Web.

Deep Learning · Robustness

Hoagy Cunningham, Jerry Wei, Zihan Wang, Andrew Persic, Alwin Peng, Jordan Abderrachid, Raj Agarwal, Bobby Chen, Andy Dau, Alek Dimitriev 等

We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to previous-generation defenses. Our system combines several key insights. First, we develop exchange classifiers that evaluate model responses in their full conversational context, which addresses vulnerabilities in last-generation systems that examine outputs in isolation. Second, we implement a two-stage classifier cascade where lightweight classifiers screen all traffic and escalate only suspicious exchanges to more expensive classifiers. Third, we train efficient linear probe classifiers and ensemble them with external classifiers to simultaneously improve robustness and reduce computational costs. Together, these techniques yield a production-grade system achieving a 40x computational cost reduction compared to our baseline exchange classifier, while maintaining a 0.05% refusal rate on production traffic. Through extensive red-teaming comprising over 1,700 hours, we demonstrate strong protection against universal jailbreaks---no attack on this system successfully elicited responses to all eight target queries comparable in detail to an undefended model. Our work establishes Constitutional Classifiers as practical and efficient safeguards for large language models.

Reinforcement Learning · Batch/Offline

Tieru Wang, Kunbao Wu, Guoshun Nan

Recent advances in offline reinforcement learning (RL) have led to the development of high-performing algorithms that achieve impressive results across standard benchmarks. However, many of these methods depend on increasingly complex planning architectures, which hinder their deployment in real-world settings due to high inference costs. To overcome this limitation, recent research has explored data augmentation techniques that offload computation from online decision-making to offline data preparation. Among these, diffusion-based generative models have shown potential in synthesizing diverse trajectories but incur significant overhead in training and data generation. In this work, we propose Trajectory Generation with Conservative Value Guidance (TGCVG), a novel trajectory-level data augmentation framework that integrates a high-performing offline policy with a learned dynamics model. To ensure that the synthesized trajectories are both high-quality and close to the original dataset distribution, we introduce a value-guided regularization during the training of the offline policy. This regularization encourages conservative action selection, effectively mitigating distributional shift during trajectory synthesis. Empirical results on standard benchmarks demonstrate that TGCVG not only improves the performance of state-of-the-art offline RL algorithms but also significantly reduces training and trajectory synthesis time. These findings highlight the effectiveness of value-aware data generation in improving both efficiency and policy performance.

Applications · Robotics

Xuening Zhang, Qi Lv, Xiang Deng, Miao Zhang, Xingbo Liu, Liqiang Nie

View transformers process multi-view observations to predict actions and have shown impressive performance in robotic manipulation. Existing methods typically extract static visual representations in a view-specific manner, leading to inadequate 3D spatial reasoning ability and a lack of dynamic adaptation. Taking inspiration from how the human brain integrates static and dynamic views to address these challenges, we propose Cortical Policy, a novel dual-stream view transformer for robotic manipulation that jointly reasons from static-view and dynamic-view streams. The static-view stream enhances spatial understanding by aligning features of geometrically consistent keypoints extracted from a pretrained 3D foundation model. The dynamic-view stream achieves adaptive adjustment through position-aware pretraining of an egocentric gaze estimation model, computationally replicating the human cortical dorsal pathway. Subsequently, the complementary view representations of both streams are integrated to determine the final actions, enabling the model to handle spatially-complex and dynamically-changing tasks under language conditions. Empirical evaluations on RLBench, the challenging COLOSSEUM benchmark, and real-world tasks demonstrate that Cortical Policy outperforms state-of-the-art baselines substantially, validating the superiority of dual-stream design for visuomotor control. Our cortex-inspired framework offers a fresh perspective for robotic manipulation and holds potential for broader application in vision-based robot control.

Computer Vision · Vision Models & Multimodal

Qinghongbing Xie, Zhaoyuan Xia, Feng Zhu, Lijun GONG, Ziyue Li, Rui Zhao, Long ZENG

Recently spatial-temporal intelligence of Visual-Language Models (VLMs) has attracted much attention due to its importance for autonomous driving, embodied AI and general AI. Existing spatial-temporal benchmarks mainly focus on egocentric (first-person) perspective reasoning using images/video contexts, or geographic reasoning with graphical context (e.g., maps), thus fail to assess VLMs' geographic spatial-temporal intelligence that requires integrating both images/video and graphical context, which is crucial for real-world scenarios such as traffic management and emergency response. To address the gaps, we introduce Geo-Temporal Reasoning benchmark (GTR-Bench), a novel challenge for geographic temporal reasoning of moving targets in a large-scale camera network. GTR-Bench is more challenging as it requires multiple perspective switches between maps and videos, joint reasoning across multiple videos with non-overlapping fields of view, and inference over spatial-temporal regions that are unobserved by any video context. Evaluations of more than 10 popular VLMs on GTR-Bench show that even the best proprietary model, Gemini-2.5-Pro (34.9\%), significantly lags behind human performance (78.61\%) on geo-temporal reasoning. Moreover, our comprehensive analysis on GTR-Bench reveals three major deficiencies of current models for geo-temporal reasoning. (1) VLMs exhibit imbalanced utilization of spatial and temporal context during reasoning. (2) they show weak temporal forecasting ability, leading to poorer performance on temporally focused tasks. (3) they lack the capability to effectively align and integrate map data with multi-view video inputs. We believe GTR-Bench offers valuable insights and opens up new opportunities for research and applications in spatial-temporal intelligence. Benchmark and code will be released at https://github.com/X-Luffy/GTR-Bench.

Tieyuan Chen, Xiaodong Chen, Haoxing Chen, Zhenzhong Lan, Weiyao Lin, Jianguo Li

We introduce Dynamic Nested Depth (DND), a novel method that improves performance for off-the-shelf LLMs by selecting critical tokens to reprocess in a nested depth manner. Specifically, at the end of the given transformer layer, DND identifies more critical tokens with a router and feeds them back for an extra round of processing, effectively "reviewing" difficult tokens while avoiding redundant computation for easier ones. The dynamic selection mechanism is tailored for precise control via two novel strategies: a router controlling loss to enhance token selection distinguishability, and a threshold control scheme to ensure selection stability. We demonstrate the effectiveness of DND by directly integrating it into pre-trained dense and MoE models during a post-training phase. On diverse benchmarks, DND boosts the performances of the dense Qwen3-1.7B, Llama3.2-1B, and Gemma3-1B by 1.88%, 2.61%, and 2.50% and the MoE Qwen3-30B-A3B by 0.87%, all with a minimal parameter and computing increase.

Optimization · Everything Else

Bruno Mlodozeniec, Pierre Ablin, Louis Béthune, Dan Busbridge, Michal Klein, Jason Ramapuram, marco cuturi

Hyperparameter tuning can dramatically impact training stability of large-scale models. Recent works on neural network parameterisations, such as μP, have shown that layer types and sizes should dictate how global hyperparameters should be rescaled in order to achieve efficient transfer across model sizes. On the other hand, the established practice for hyperparameter optimisation search is to look for optimal global base values that apply at some fixed model scale. We transfer hyperparameters across all scaling axes: width and depth, using an extension of CompleteP (Dey et al., 2025), training horizon, and batch size. Our study covers all optimisation hyperparameters of modern models: learning rates, Adam parameters, weight decay, initialisation scales, and residual block multipliers. Lastly, we demonstrate that hyperparameter transfer holds even in the per-layer hyperparameter regime. We characterise the empirical challenges of navigating the high-dimensional hyperparameter landscape, and propose practical guidelines for tackling this optimisation problem. We suggest a simplified parameterisation of the hyperparameter space that reduces the dimensionality of the search-space at no performance cost. Our experiments demonstrate training speed improvements when applying transferred hyperparameters to Large Language Models.

Computer Vision · Image and Video Generation

Qingyang Mao, Qi Cai, Yehao Li, Yingwei Pan, Mingyue Cheng, Ting Yao, Qi Liu, Tao Mei

Recent advances in diffusion models have brought remarkable visual fidelity to instruction-guided image editing. However, their global denoising process inherently entangles the edited region with the entire image context, leading to unintended spurious modifications and compromised adherence to editing instructions. In contrast, autoregressive models offer a distinct paradigm by formulating image synthesis as a sequential process over discrete visual tokens. Their causal and compositional mechanism naturally circumvents the adherence challenges of diffusion-based methods. In this paper, we present VAREdit, a visual autoregressive (VAR) framework that reframes image editing as a next-scale prediction problem. Conditioned on source image features and text instructions, VAREdit generates multi-scale target features to achieve precise edits. A core challenge in this paradigm is how to effectively condition the source image tokens. We observe that finest-scale source features cannot effectively guide the prediction of coarser target features. To bridge this gap, we introduce a Scale-Aligned Reference (SAR) module, which injects scale-matched conditioning information into the first self-attention layer. VAREdit demonstrates significant advancements in both editing adherence and efficiency. On EMU-Edit and PIE-Bench benchmarks, VAREdit outperforms leading diffusion-based methods by a substantial margin in terms of both CLIP and GPT scores. Moreover, VAREdit completes a 512$\times$512 editing in 1.2 seconds, making it 2.2$\times$ faster than the similarly sized UltraEdit. Code is available at: https://github.com/HiDream-ai/VAREdit.

Applications · Robotics

Y. Isabel Liu, Bowen Li, Benjamin Eysenbach, Tom Silver

Long-horizon decision-making with sparse rewards and continuous states and actions remains a fundamental challenge in AI and robotics. Task and motion planning (TAMP) is a model-based framework that addresses this challenge by planning hierarchically with abstract actions (options). These options are manually defined, limiting the agent to behaviors that we as human engineers know how to program (pick, place, move). In this work, we propose Shortcut Learning for Abstract Planning (SLAP), a method that leverages existing TAMP options to automatically discover new ones. Our key idea is to use model-free reinforcement learning (RL) to learn *shortcuts* in the abstract planning graph induced by the existing options in TAMP. Without any additional assumptions or inputs, shortcut learning leads to shorter solutions than pure planning, and higher task success rates than flat and hierarchical RL. Qualitatively, SLAP discovers dynamic physical improvisations (e.g., slap, wiggle, wipe) that differ significantly from the manually-defined ones. In experiments in four simulated robotic environments, we show that SLAP solves and generalizes to a wide range of tasks, reducing overall plan lengths by over 50\% and consistently outperforming planning and RL baselines.

Yuhao Mao, Yani Zhang, Martin Vechev

Neural network certification methods heavily rely on convex relaxations to provide robustness guarantees. However, these relaxations are often imprecise: even the most accurate single-neuron relaxation is incomplete for general ReLU networks, a limitation known as the *single-neuron convex barrier*. While multi-neuron relaxations have been heuristically applied to address this issue, two central questions arise: (i) whether they overcome the convex barrier, and if not, (ii) whether they offer theoretical capabilities beyond those of single-neuron relaxations. In this work, we present the first rigorous analysis of the expressiveness of multi-neuron relaxations. Perhaps surprisingly, we show that they are inherently incomplete, even when allocated sufficient resources to capture finitely many neurons and layers optimally. This result extends the single-neuron barrier to a *universal convex barrier* for neural network certification. On the positive side, we show that completeness can be achieved by either (i) augmenting the network with a polynomial number of carefully designed ReLU neurons or (ii) partitioning the input domain into convex sub-polytopes, thereby distinguishing multi-neuron relaxations from single-neuron ones which are unable to realize the former and have worse partition complexity for the latter. Our findings establish a foundation for multi-neuron relaxations and point to new directions for certified robustness, including training methods tailored to multi-neuron relaxations and verification methods with multi-neuron relaxations as the main subroutine.

Computer Vision · Vision Models & Multimodal

Or Hirschorn, Shai Avidan

Category-Agnostic Pose Estimation (CAPE) localizes keypoints across diverse object categories with a single model, using one or few annotated support images. Recent works have shown that using a pose-graph (i.e., treating keypoints as nodes in a graph rather than isolated points) helps handle occlusions and break symmetry. However, these methods assume a given pose-graph with equal-weight edges, leading to suboptimal results. We introduce EdgeCape, a novel framework that overcomes these limitations by predicting the graph's edge weights in order to optimize localization. To further leverage structural (i.e., graph) priors, we propose integrating Markov Attention Bias, which modulates the self-attention interaction between nodes based on the number of hops between them. We show that this improves the model’s ability to capture global spatial dependencies. Evaluated on the MP-100 benchmark, which includes 100 categories and over 20K images, EdgeCape achieves state-of-the-art results in the 1-shot and 5-shot settings, significantly improving keypoint localization accuracy.

Applications · Language, Speech and Dialog

Yingyi Zhang, Junyi Li, Wenlin Zhang, Pengyue Jia, Xianneng Li, Yichao Wang, Derong Xu, Yi Wen, Huifeng Guo, Yong Liu 等

Personalized large language models (LLMs) rely on memory retrieval to incorporate user-specific histories, preferences, and contexts. Existing approaches either overload the LLM by feeding all the user's past memory into the prompt, which is costly and unscalable, or simplify retrieval into a one-shot similarity search, which captures only surface matches. Cognitive science, however, shows that human memory operates through a dual process: Familiarity, offering fast but coarse recognition, and Recollection, enabling deliberate, chain-like reconstruction for deeply recovering episodic content. Current systems lack both the ability to perform recollection retrieval and mechanisms to adaptively switch between the dual retrieval paths, leading to either insufficient recall or the inclusion of noise. To address this, we propose RF-Mem (Recollection–Familiarity Memory Retrieval), a familiarity uncertainty-guided dual-path memory retriever. RF-Mem measures the familiarity signal through the mean score and entropy. High familiarity leads to the direct top-$K$ Familiarity retrieval path, while low familiarity activates the Recollection path. In the Recollection path, the system clusters candidate memories and applies $\alpha$-mix with the query to iteratively expand evidence in embedding space, simulating deliberate contextual reconstruction. This design embeds human-like dual-process recognition into the retriever, avoiding full-context overhead and enabling scalable, adaptive personalization. Experiments across three benchmarks and corpus scales demonstrate that RF-Mem consistently outperforms both one-shot retrieval and full-context reasoning under fixed budget and latency constraints. Our code can be found in the Reproducibility Statement.

Applications · Language, Speech and Dialog

Zeyu Jin, Songtao Zhou, Haoyu Wang, Minghao Tian, Kaifeng Yun, Zhuo Chen, Xiaoyu Qin, Jia Jia

The recent advancement of Artificial Intelligence Generated Content (AIGC) has led to significant strides in modeling human interaction, particularly in the context of multimodal dialogue. While current methods impressively generate realistic dialogue in isolated modalities like speech or vision, challenges remain in controllable Multimodal Dialogue Generation (MDG). This paper focuses on the natural alignment between speech, vision, and text in human interaction, aiming for expressive dialogue generation through multimodal conditional control. To address the insufficient richness and diversity of dialogue expressiveness in existing datasets, we introduce a novel multimodal dialogue annotation pipeline to curate dialogues from movies and TV series with fine-grained annotations in interactional characteristics. The resulting MM-Dia dataset (360+ hours, 54,700 dialogues) facilitates explicitly controlled MDG, specifically through style-controllable dialogue speech synthesis. In parallel, MM-Dia-Bench (309 highly expressive dialogues with visible single-/dual-speaker scenes) serves as a rigorous testbed for implicit cross-modal MDG control, evaluating audio-visual style consistency across modalities. Extensive experiments demonstrate that training on MM-Dia significantly enhances fine-grained controllability, while benchmarks on MM-Dia-Bench reveal limitations in current frameworks to replicate the nuanced expressiveness of human interaction. These findings provides new insights and challenges for multimodal conditional dialogue generation.

Junyu Luo, Jinsheng Huang, Yang Xu, Lutong Zou, Xiao Luo, Bohan Wu, Yifan Wang, Wei Ju, Ming Zhang

Unsupervised domain adaptive hashing transfers knowledge from labeled source domains to unlabeled target domains, addressing domain shift challenges in real-world retrieval tasks. Existing methods face two critical limitations: target domain noise severely misleads model training, and indiscriminate domain alignment strategies treat all target samples equally, potentially distorting essential feature structures. We propose an uncertainty-aware adaptive hashing approach that addresses these challenges through a hierarchical conformal calibration framework. At the semantic level, we employ conformal inference to generate confidence prediction sets, replacing single pseudo-labels with set-based predictions whose sizes directly quantify sample reliability for weighted pseudo-label learning and domain alignment. This enables the model to focus on reliable samples while suppressing noise. At the representation level, we predict the stability of individual hash bits, where bit-level confidence guides a robust weighted quantization loss and enables dynamic weighted Hamming distance during retrieval, fundamentally enhancing hash code quality and retrieval robustness. Through this hierarchical calibration mechanism, our method achieves more adaptive and robust cross-domain knowledge transfer. Extensive experiments on multiple benchmark datasets demonstrate significant improvements over existing approaches, validating the effectiveness and superiority of our method.

Social Aspects · Fairness, Equity, Justice and Safety

Panjia Qiu, Mingyuan Fan, Cen Chen, Daixin Wang

Large language models (LLMs) have recently achieved impressive progress in knowledge-intensive and reasoning tasks. However, their tendency to produce fabricated or factually inconsistent content remains a fundamental challenge to their practical deployment. To address this issue, we propose Negative-Direction Aware Decoding (NDAD), a novel decoding method that identifies and exploits hallucination signals as repulsive directions in the model’s representation space, thereby improving factual adherence without retraining. Specifically, NDAD elicits hallucination-leaning signals by selectively masking critical attention heads, which exposes unstable hypotheses that the model would otherwise amplify during generation. To regulate the influence of these signals, NDAD employs two complementary weights: a global alignment weight measuring how well the induced signal aligns with the layer’s native activations (thus quantifying its referential utility) and a local weight estimating whether low-probability tokens in the masked distribution are likely to evolve toward the final output. Based on the weights, we derive a latent hallucination distribution that serves as the negative direction. A lightweight gradient-descent step then subtracts mass from hallucination-prone regions of the output distribution, adjusting the final logits while preserving the model’s high-confidence predictions. Extensive experiments across multiple LLMs and diverse benchmark datasets demonstrate that NDAD consistently enhances factual reliability without requiring additional training or external knowledge.

Theory · Reinforcement Learning and Planning

Haochen Zhang, Zhong Zheng, Lingzhou Xue

We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minimax worst-case regret, but their gap-dependent bounds remain coarse and fail to fully capture the structure of suboptimality gaps. To address this limitation, we establish fine-grained gap-dependent regret guarantees for both UCB-based and non-UCB-based algorithms. In the UCB-based setting, we develop a novel analytical framework that explicitly separates the analysis of optimal and suboptimal state-action pairs, yielding the first fine-grained regret upper bound for UCB-Hoeffding (Jin et al., 2018). In the non-UCB-based setting, we revisit the only existing algorithm, AMB (Xu et al., 2021), and identify two issues in its design and analysis: improper truncation in the $Q$-updates and violation of the martingale difference condition in the concentration argument. To resolve these issues, we propose two refinements of AMB: the UCB-based ULCB-Hoeffding and the non-UCB-based Refined AMB. For ULCB-Hoeffding, we establish the same fine-grained regret bound as UCB-Hoeffding by applying our fine-grained framework, highlighting its broad applicability. For Refined AMB, we derive a rigorous fine-grained gap-dependent regret bound in the non-UCB setting and demonstrate consistent empirical improvements over the original AMB.

Chao Wang, Tao Yang, Hongtao Tian, Yunsheng Shi, Qiyao Ma, XiaotaoLiu, Ting Yao, Wenbo Ding

Critic-free methods like GRPO reduce memory demands by estimating advantages from multiple rollouts but tend to converge slowly, as critical learning signals are diluted by an abundance of uninformative samples and tokens. To tackle this challenge, we propose the **Dynamic Dual-Level Down-Sampling (D$^3$S)** framework that prioritizes the most informative samples and tokens across groups to improve the efficiency of policy optimization. D$^3$S operates along two levels: (1) the sample-level, which selects a subset of rollouts to maximize advantage variance ($\text{Var}(A)$). We theoretically proved that this selection is positively correlated with the upper bound of the policy gradient norms, yielding higher policy gradients. (2) the token-level, which prioritizes tokens with a high product of advantage magnitude and policy entropy ($|A_{i,t}|\times H_{i,t}$), focusing updates on tokens where the policy is both uncertain and impactful. Moreover, to prevent overfitting to high-signal data, D$^3$S employs a dynamic down-sampling schedule inspired by curriculum learning. This schedule starts with aggressive down-sampling to accelerate early learning and gradually relaxes to promote robust generalization. Extensive experiments on Qwen2.5 and Llama3.1 demonstrate that integrating D$^3$S into advanced RL algorithms achieves state-of-the-art performance with generalization while requiring fewer samples and tokens across diverse reasoning benchmarks.

Deep Learning · Robustness

Claus Hofmann, Christian Huber, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter, Werner Zellinger

Out-of-distribution (OOD) detection, which maps high-dimensional data into a scalar OOD score, is critical for the reliable deployment of machine learning models. A key challenge in recent research is how to effectively leverage and aggregate token embeddings from language models to obtain the OOD score. In this work, we propose AP-OOD, a novel OOD detection method for natural language that goes beyond simple average-based aggregation by exploiting token-level information. AP-OOD is a semi-supervised approach that flexibly interpolates between unsupervised and supervised settings, enabling the use of limited auxiliary outlier data. Empirically, AP-OOD sets a new state of the art in OOD detection for text: in the unsupervised setting, it reduces the FPR95 (false positive rate at 95% true positives) from 27.77% to 5.91% on XSUM summarization, and from 75.19% to 68.13% on WMT15 En–Fr translation.

Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang

We introduce a **variational reasoning** framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where *an implicit weighting by model accuracy* naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models.

Deep Learning · Everything Else

Changzhi Zhou, Ao Liu, Yuchi Deng, Zhiying Zeng, Tao Zhang, Haotian Zhu, Jianwei Cai, Yue Mao, Chenchen Zhang, Lingyun Tan 等

Large Language Models (LLMs) have shown impressive performance across diverse domains, with code generation emerging as a particularly prominent application. However, existing benchmarks designed to evaluate code generation exhibit several critical limitations. First, most rely on manual annotations, which are time-consuming and difficult to scale across programming languages and problem complexities. Second, the majority focus primarily on Python, while the few multilingual benchmarks suffer from limited difficulty and imbalanced language coverage. To overcome these challenges, we present AutoCodeGen, an automated framework for constructing high-difficulty, multilingual code generation datasets without manual annotations. Our approach guarantees correctness and completeness by generating test inputs with LLMs, obtaining test outputs within a multilingual sandbox, and further enhancing quality through reverse problem generation and multi-stage filtering. Based on this novel method, we introduce AutoCodeBench, a large-scale benchmark suite spanning 20 programming languages with balanced coverage. AutoCodeBench is designed to rigorously evaluate LLMs on diverse, challenging, and realistic multilingual programming tasks. Extensive experiments reveal that even state-of-the-art models struggle on these tasks, particularly in low-resource languages. Besides, we release complementary training and evaluation resources, including a large-scale, verifiable multilingual instruction dataset generated via the same pipeline, as well as a multilingual sandbox with high-concurrency support. We hope these contributions will provide a solid foundation for future research and inspire the community to explore more automatic and scalable approaches to multilingual code generation, with a particular emphasis on advancing progress in low-resource languages.