We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads. Super is a 120B-parameter, 12B-active multimodal model, while Lightning is a smaller 30B-parameter, 3B-active text model; both designed for efficient deployment. Both models combine large-scale distillation, long-context training, and native speculative decoding, while Super further incorporates Indic continued pretraining and agentic software-engineering mid-training. We develop a comprehensive post-training pipeline spanning supervised fine-tuning and reinforcement learning (RLVR and RLHF), complemented in Super by specialized teacher training and multi- teacher on-policy distillation (MOPD). This transforms Super from a text-only base model into a multimodal agent capable of reasoning over text, images, video, and interactive tool environments. We further explore test-time scaling through parallel agent execution and self-verification. Across training and deployment, we jointly optimize capability and efficiency. Indic continued pretraining improves Indian-language benchmarks by up to 9.82 percentage points, while agentic mid-training strengthens software-engineering capabilities and robustness across agent harnesses. The post-trained Super model achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra despite using approximately 4.6x fewer active parameters. Post-training MTP boosting improves speculative- decoding acceptance length by up to 21.8% under probabilistic draft sampling, while NVFP4 quantization achieves 99.62% median accuracy recovery relative to BF16. Inference optimizations enable up to 4,856 output tokens/s/GPU on GB200 while sustaining at least 50 tokens/s/user.
Zehao Wang, Hanzhu Chen, Runquan Gui, Zhe Wang, Lin Yang
Reinforcement Learning with Verifiable Rewards (RLVR) derives its learning signal from binary rewards via on-policy exploration and becomes a powerful paradigm for improving the reasoning of large language models. Yet it faces a learning cliff on problems beyond model's current ability: when every rollout fails, the samples reveal nothing about a correct solution, and group-relative estimators (e.g., GRPO, RLOO) collapse the update to zero advantage. Expert trajectories offer a remedy, but they are incompatible with the current policy and often lie in the student's low-probability regions, so the surviving updates demand large parameter shifts and decay into surface-level imitation rather than transferable reasoning. We argue that a useful learning signal on hard problems must be both verifiably correct and sufficiently compatible with the current policy. We propose Policy-Compatible Reinforcement Learning (PICO), which performs distribution-constrained joint decoding: expert data guides decoding at the token level while preserving the student's relative token probabilities, and a dynamic top-k mechanism confines the sampling distribution under a finite divergence budget, yielding trajectories that are verified and policy-compatible by construction. These trajectories are optimized jointly with on-policy rollouts under a mixed-behavior objective that mitigates their distribution mismatch via importance sampling. Experiments across reasoning diverse datasets and agentic benchmarks demonstrate that PICO consistently outperforms standard RLVR and prior off-policy baselines.
Historical maps contain dense morphological and semantic information about past urban environments, but many digitization workflows focus primarily on extracting geometry, and do not capture cartographic semantics such as building use and construction materials. This study introduces ArchiveLens, a generative spatial knowledge framework that operationalizes historical maps as entity-centric, machine-queryable geospatial databases. The pipeline decouples morphological and semantic reconstruction through three stages: tiled YOLOv11-seg instance segmentation for building footprint extraction; deterministic material classification via hue, saturation, and value (HSV)-based color thresholds; and localized attribute parsing using a quantized vision-language model constrained by domain-specific prompts. Extracted entities are integrated into a hybrid Spatial-Temporal Retrieval-Augmented Generation (ST-RAG) architecture that combines dense semantic retrieval with symbolic spatio-temporal filtering and mandatory provenance grounding. Applied to 445 georeferenced Sanborn map sheets of Chicago (1918-1950), the framework achieves high geometric and semantic accuracy. Beyond performance, ArchiveLens advances GIScience by formalizing historical cartography as structured spatial knowledge representation, allowing researchers to query building attributes and compare spatial patterns across map sheets and years.
Anda Tang, Xuanlin Yang, Junjie Wang, Zhouchen Lin
Large scale language model~(LLM) pretraining is increasingly bottlenecked by optimizer efficiency, driving optimizer design from vector-aware methods such as AdamW to matrix-aware methods. Matrix-aware optimizers such as Muon exploit matrix structure but treat layers independently, neglecting cross-layer correlations. Tensor-aware optimizers are therefore needed, yet existing ones rely on a matricization-based tensor algebra and remain restricted to shallow stacking and specific modules. In this paper, we propose \textbf{TUON}, a novel optimizer built on a transform-based tensor algebra derived from the Tensor-SVD (T-SVD). Unlike methods that polarize a globally unfolded matrix, TUON mixes layers via a unitary transform $\boldsymbol{Q}$ and then polarizes each transformed slice, and inverts the transform to recover the update. This mix-then-separate strategy captures cross-layer correlations while preserving per-layer diversity, avoiding the structural dimension imbalance and cross-layer misalignment of unfolding. Thus it successfully scales to more layers and diverse modules beyond QKV. Theoretically, we prove that TUON performs steepest descent under a $\boldsymbol{Q}$-transformed tensor spectral norm, and identify its update as the tensor polar factor of the T-SVD. We further establish transform non-redundancy, norm and smoothness comparisons with Muon and TEON, and a convergence guarantee. Empirically, TUON improves consistently over Muon and TEON on GPT-124M/350M and Qwen-0.6B/4B, with ablations confirming the transformation mechanism, cross-layer structure beyond two-layer stacking, adaptability beyond QKV, and robustness to the polarization method.
Anda Tang, Junjie Wang, Xuanlin Yang, Cong Fang, Zhouchen Lin
Learning rate decay (LRD) is critical for training high-performance models, yet most designs remain empirically driven. Although the Universal Budget Aware (UBA) LRD offers a theoretical framework, its reliance on SGD dynamics limits its applicability to modern Adam-type optimizers and leaves its key `optimization difficulty parameter' opaque. To bridge this gap, we propose the Universal Training Adaptive (UTA) LRD. Unlike UBA's fixed offline trajectory anchored solely to iterations, UTA treats LRD as a closed-loop shape-and-scale problem. By continuous-time formulation, UTA is training-state adaptive with segment-wise optimal shape. This adaptivity links external iterations with internal training states, enabling a near-optimal path in both progression shape and learning rate (LR) scale, a property unattainable by other LRDs, including UBA. Empirically, we demonstrate consistent improvements across language models (LLaMA 60M to 1B) and vision models (ResNet50, ViT-B) on ImageNet with plug-and-play ease and negligible overhead. Extensive ablation studies further confirm UTA's robustness across dimensions, including peak LR, final decay ratio, its parameter $\varphi_0$, component efficacy and generalization to fine-tuning scenarios, underscoring its practical implementability.
Han Guo, Songlin Yang, Tarushii Goel, Eric P. Xing, Tri Dao, Yoon Kim
AI 速览：提出对数线性注意力，用对数增长的多隐藏状态替代固定大小隐藏状态，在保持矩阵乘法并行性的同时兼顾线性注意力效率与softmax注意力表达力。
The attention mechanism in Transformers is an important primitive for accurate and scalable sequence modeling. Its quadratic-compute and linear-memory complexity however remain significant bottlenecks. Linear attention and state-space models enable linear-time, constant-memory sequence modeling and can moreover be trained efficiently through matmul-rich parallelization across sequence length. However, at their core these models are still RNNs, and thus their use of a fixed-size hidden state to model the context is a fundamental limitation. This paper develops log-linear attention, an attention mechanism that balances linear attention's efficiency and the expressiveness of softmax attention. Log-linear attention replaces the fixed-size hidden state with a logarithmically growing set of hidden states. We show that with a particular growth function, log-linear attention admits a similarly matmul-rich parallel form whose compute cost is log-linear in sequence length. Log-linear attention is a general framework and can be applied on top of existing linear attention variants. As case studies, we instantiate log-linear variants of two recent architectures -- Mamba-2 and Gated DeltaNet -- and find they perform well compared to their linear-time variants.
Linear Transformers have gained attention as efficient alternatives to standard Transformers, but their performance in retrieval and long-context tasks has been limited. To address these limitations, recent work has explored two distinct mechanisms: gating for adaptive memory control and the delta update rule for precise memory modifications. We observe that these mechanisms are complementary: gating enables rapid memory erasure while the delta rule facilitates targeted updates. Building on this insight, we introduce the gated delta rule and develop a parallel training algorithm optimized for modern hardware. Our proposed architecture, Gated DeltaNet, consistently surpasses existing models like Mamba2 and DeltaNet across multiple benchmarks, including language modeling, common-sense reasoning, in-context retrieval, length extrapolation, and long-context understanding. We further enhance performance by developing hybrid architectures that combine Gated DeltaNet layers with sliding window attention or Mamba2 layers, achieving both improved training efficiency and superior task performance.