arXiv:2511.23310v2 Announce Type: replace Abstract: Existing reinforcement learning (RL)-based post-training methods for large language models have advanced rapidly, yet their design has largely been guided by heuristics rather than systematic theoretical principles. This gap limits our understanding of the properties of the gradient estimators and the associated optimization algorithms, thereby constraining opportunities to improve training stability and overall performance. In this work, we provide a unified theoretical framework that characterizes the statistical properties of commonly used policy-gradient estimators […]

Ver mais

arXiv:2604.16917v1 Announce Type: new Abstract: Languages encode distinct abstractions and inductive priors, yet most large language models (LLMs) overlook this diversity by reasoning in a single dominant language. In this work, we introduce x1, a family of reasoning models that can adaptively reason in an advantageous language on a per-instance basis. To isolate the effect of reasoning-language choice, x1 is constructed without expanding the model’s knowledge boundaries and is trained by contrasting linguistically distinct reasoning trajectories for the […]

Ver mais

arXiv:2603.05686v1 Announce Type: new Abstract: We introduce a perception-related function, OWL, designed to address the complex challenges of 3D perception during motion. It derives its values directly from two fundamental visual motion cues, with one set of cue values per point per time instant. During motion, two visual motion cues relative to a fixation point emerge: 1) perceived local visual looming of points near the fixation point, and 2) perceived rotation of the rigid object relative to the […]

Ver mais

arXiv:2605.13915v1 Announce Type: new Abstract: Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplication has become a critical bottleneck on modern AI accelerators. On architectures with decoupled compute units (e.g., Ascend NPUs), dequantization operations can consume more cycles than the matrix multiplication itself, leaving the high-throughput tensor cores underutilized. This paper presents Multi-Scale Dequant (MSD), a quantization framework that removes weight/KV dequantization from the GEMM […]

Ver mais

arXiv:2307.07753v2 Announce Type: replace-cross Abstract: In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks. The key idea is to exploit scalable and structured posteriors of neural networks as informative priors with generalization guarantees. Our learned priors provide expressive probabilistic representations at large scale, like Bayesian counterparts of pre-trained models on ImageNet, and further produce non-vacuous generalization bounds. We also extend this idea to a continual learning framework, […]

Ver mais

arXiv:2601.18830v1 Announce Type: new Abstract: Accurate multi-label classification of electrocardiogram (ECG) signals remains challenging due to the coexistence of multiple cardiac conditions, pronounced class imbalance, and long-range temporal dependencies in multi-lead recordings. Although recent studies increasingly rely on deep and stacked recurrent architectures, the necessity and clinical justification of such architectural complexity have not been rigorously examined. In this work, we perform a systematic comparative evaluation of convolutional neural networks (CNNs) combined with multiple recurrent configurations, including LSTM, […]

Ver mais

arXiv:2601.00864v1 Announce Type: cross Abstract: Graphs are commonly used in machine learning to model relationships between instances. Consider the task of predicting the political preferences of users in a social network; to solve this task one should consider, both, the features of each individual user and the relationships between them. However, oftentimes one is not interested in the label of a single instance but rather in the distribution of labels over a set of instances; e.g., when predicting […]

Ver mais

Hybrid architectures combining state-space models with attention have achieved strong efficiency-quality tradeoffs, yet existing approaches either apply attention uniformly or learn static sparse patterns. This misses a key opportunity: emph{attention demand should decrease over time as recurring patterns become familiar}. We present a surprising finding from analyzing GPT-2 models: textbf{88%} of attention operations retrieve information already predictable from the model’s hidden state, and this redundancy does emph{not} decrease during training. Motivated by this observation, we introduce textbf{ours{}} (textbf{C}onsolidation-based […]

Ver mais