Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in OpenAI o1 blog and DeepSeek R1 technical report), thus the community still struggles to reproduce their RL training results. We propose the Decoupled Clip and Dynamic sAmpling Policy Optimization (DAPO) algorithm, and fully opensource a state-of-the-art large-scale RL system that achieves 50 points on AIME 2024 using Qwen2.5-32B

Despite the impressive performance of large language models (LLMs), the process of endowing them with new capabilities--such as mathematical reasoning-- remains largely empirical and opaque. A critical open question is whether reasoning abilities stem from the entire model, specific modules, or are merely artifacts of overfitting. In this work, we hypothesize that the reasoning capabilities in welltrained LLMs are primarily attributed to the output projection module (o_proj) in the Transformer's multi-head self-attention (MHSA) module. To support this hypothesis, we introduce Stethoscope for Networks (SfN), a suite of diagnostic tools designed to probe and analyze the internal behaviors of LLMs. Using SfN, we provide both circumstantial and empirical evidence suggesting that o_proj plays a central role in enabling reasoning, whereas other modules contribute more to fluent dialogue. These findings offer a new perspective on LLM interpretability and open avenues for more targeted training strategies, potentially enabling more efficient and specialized LLMs.

We investigate scaling laws for stochastic momentum algorithms with small batch on the power law random features model, parameterized by data complexity, target complexity, and model size. When trained with a stochastic momentum algorithm, our analysis reveals four distinct loss curve shapes determined by varying data-target complexities. While traditional stochastic gradient descent with momentum (SGD-M) yields identical scaling law exponents to SGD, dimension-adapted Nesterov acceleration (DANA) improves these exponents by scaling momentum hyperparameters based on model size and data complexity. This outscaling phenomenon, which also improves compute-optimal scaling behavior, is achieved by DANA across a broad range of data and target complexities, while traditional methods fall short. Extensive experiments on high-dimensional synthetic quadratics validate our theoretical predictions and large-scale text experiments with LSTMs show DANA's improved loss exponents over SGD hold in a practical setting.

Foundation models trained on web-scale data have revolutionized robotics, but their application to low-level control remains largely limited to behavioral cloning. Drawing inspiration from the success of the reinforcement learning stage in finetuning large language models, we propose a two-stage post-training approach for robotics.

Federated continual learning (FCL) has garnered increasing attention for its ability to support distributed computation in environments with evolving data distributions. However, the emergence of new tasks introduces both temporal and cross-client shifts, making catastrophic forgetting a critical challenge. Most existing works aggregate knowledge from clients into a global model, which may not enhance client performance since irrelevant knowledge could introduce interference, especially in heterogeneous scenarios. Additionally, directly applying decentralized approaches to FCL suffers from ineffective group formation caused by task changes. To address these challenges, we propose a decentralized dynamic cooperation framework for FCL, where clients establish dynamic cooperative learning coalitions to balance the acquisition of new knowledge and the retention of prior learning, thereby obtaining personalized models. To maximize model performance, each client engages in selective cooperation, dynamically allying with others who offer meaningful performance gains.

Current parameter-efficient fine-tuning methods for adapting pre-trained language models to downstream tasks are susceptible to interference from noisy data. Conventional noise-handling approaches either rely on laborious data pre-processing or employ model architecture modifications prone to error accumulation. In contrast to existing noise-process paradigms, we propose a noise-robust adaptation method via asymmetric LoRA poisoning experts (LoPE), a novel framework that enhances model robustness to noise only with generated noisy data. Drawing inspiration from the mixture-of-experts architecture, LoPE strategically integrates a dedicated poisoning expert in an asymmetric LoRA configuration. Through a two-stage paradigm, LoPE performs noise injection on the poisoning expert during finetuning to enhance its noise discrimination and processing ability. During inference, we selectively mask the dedicated poisoning expert to leverage purified knowledge acquired by normal experts for noise-robust output. Extensive experiments demonstrate that LoPE achieves strong performance and robustness purely through the low-cost noise injection, which completely eliminates the requirement of data cleaning.

However, conventional training methods based on surrogate gradients and Backpropagation Through Time (BPTT) not only lag behind Artificial Neural Networks (ANNs) in performance, but also incur significant computational and memory overheads that grow linearly with the temporal dimension. To enable high-performance SNN training under limited computational resources, we propose an enhanced self-distillation framework, jointly optimized with rate-based backpropagation. Specifically, the firing rates of intermediate SNN layers are projected onto lightweight ANN branches, and high-quality knowledge generated by the model itself is used to optimize substructures through the ANN pathways. Unlike traditional self-distillation paradigms, we observe that low-quality self-generated knowledge may hinder convergence. To address this, we decouple the teacher signal into reliable and unreliable components, ensuring that only reliable knowledge is used to guide the optimization of the model. Extensive experiments on CIFAR-10, CIFAR-100, CIFAR10-DVS, and ImageNet demonstrate that our method reduces training complexity while achieving high-performance SNN training.

Brain-inspired spiking neural networks (SNNs) promise to be a low-power alternative to computationally intensive artificial neural networks (ANNs), although performance gaps persist. Recent studies have improved the performance of SNNs through knowledge distillation, but rely on large teacher models or introduce additional training overhead. In this paper, we show that SNNs can be naturally deconstructed into multiple submodels for efficient self-distillation. We treat each timestep instance of the SNN as a submodel and evaluate its output confidence, thus efficiently identifying the strong and the weak. Based on this strong and weak relationship, we propose two efficient self-distillation schemes: (1) Strong2Weak: During training, the stronger "teacher" guides the weaker "student", effectively improving overall performance.

While federated learning (FL) and differential privacy (DP) have been extensively studied, their application to automatic speech recognition (ASR) remains largely unexplored due to the challenges in training large transformer models. Specifically, large models further exacerbate issues in FL as they are particularly susceptible to gradient heterogeneity across layers, unlike the relatively uniform gradient behavior observed in shallow models. As a result, prior works struggle to converge with standard optimization techniques, even in the absence of DP mechanisms. To the best of our knowledge, no existing work establishes a competitive, practical recipe for FL with DP in the context of ASR. To address this gap, we establish the first benchmark for FL with DP in end-to-end ASR. Our approach centers on per-layer clipping and layer-wise gradient normalization: theoretical analysis reveals that these techniques together mitigate clipping bias and gradient heterogeneity across layers in deeper models. Consistent with these theoretical insights, our empirical results show that FL with DP is viable under strong privacy guarantees, provided a population of at least several million users. Specifically, we achieve user-level (7.2, 10 9)-DP (resp.

Language models (LMs) are increasingly being deployed to perform autonomous data analyses. However, their data awareness--the ability to recognize, reason over, and appropriately handle data artifacts such as missing values, outliers, and logical inconsistencies--remains underexplored. These artifacts are especially common in real-world tabular data and, if mishandled, can significantly compromise the validity of analytical conclusions. To address this gap, we present RADAR, a benchmark for systematically evaluating data-aware reasoning on tabular data. We develop a framework to simulate data artifacts via programmatic perturbations to enable targeted evaluation of model behavior. RADAR comprises 2980 table query pairs, grounded in real-world data spanning 9 domains and 5 data artifact types. In addition to evaluating artifact handling, RADAR systematically varies table size to study how reasoning performance holds when increasing table size. Our evaluation reveals that, despite decent performance on tables without data artifacts, frontier models degrade significantly when data artifacts are introduced, exposing critical gaps in their capacity for robust, data-aware analysis. Designed to be flexible and extensible, RADAR supports diverse perturbation types and controllable table sizes, offering a valuable resource for advancing tabular reasoning.1