3arXiv cs.LG (Machine Learning)·
Transformer-guided swarm intelligence framework for low-resource neural architecture search
A new arXiv preprint proposes a hybrid NAS framework combining an autoregressive Transformer controller trained via reinforcement learning with an Artificial Bee Colony metaheuristic for local search. The system targets consumer-grade hardware (NVIDIA RTX 3060), completing architecture search in ~3 hours and finding compact models: 84.85% on CIFAR-10 with ~174K parameters and F1=0.71 on fraud detection with ~4,600 parameters. A dynamic entropy mechanism is introduced to prevent premature convergence during RL training. The work addresses the democratization angle of NAS, positioning results as suitable for edge deployment.
Related guides (2)
Related events (8)
Nvidia Nemotron 3 Ultra: hybrid Mamba-transformer open-weights model targeting agentic workloads
Nvidia released Nemotron 3 Ultra, a 550B parameter (55B active) hybrid Mamba-transformer mixture-of-experts model with a 1M token context window, publishing weights, training data, and RL environments under an open license. The model ranks as the highest-scoring U.S. open-weights model on the Artificial Analysis Intelligence Index (47.7-48.2) and is approximately three times faster than comparable open-weights rivals, though it trails leading Chinese models like Kimi K2.6 and DeepSeek V4 Pro on intelligence benchmarks. Nvidia used a novel Multi-Teacher On-Policy Distillation approach with 10+ specialized teacher models and trained using NVFP4 quantization. The release is strategically motivated by Nvidia's interest in a healthy open-weights ecosystem that drives AI semiconductor adoption.
Agency-transferring technique improves RL policy training by bootstrapping from baseline policies
A new arXiv paper proposes a model-free reinforcement learning method that embeds an existing suboptimal baseline policy into training via an arbitration mechanism, progressively transferring control from the baseline to a trainable neural network. The approach yields high goal-reaching rates from the start of training and produces a standalone policy that outperforms the baseline without requiring it at inference time. Theoretical bounds on goal-reaching probability are derived, and empirical results on continuous-control benchmarks show competitive or superior returns compared to existing methods.
Roofline-inspired scaling model predicts Transformer fine-tuning energy consumption across GPU configurations
A new arXiv preprint presents a framework for modeling energy consumption during Transformer training on multiple GPUs, using BERT architectural sweeps to relate measured energy to proxies for compute, memory traffic, and hardware efficiency. The approach adapts roofline modeling with a speedup-based hardware-efficiency factor that accounts for tensor parallelism and fully sharded data parallelism. The resulting scaling law accurately predicts training energy across heterogeneous configurations, targeting sustainable and cost-aware system design.
AgenticRL: Self-refining LLM-guided reward design and policy refinement for UAV navigation
AgenticRL is a framework that uses a multimodal GPT agent to automate reward function generation, policy training via PPO, and closed-loop self-refinement for UAV navigation tasks. The agent evaluates trained policies through diagnostic feedback, identifies failure modes, and iteratively refines rewards without human intervention. Evaluated across five navigation tasks, the closed-loop refinement improves policy behavior by 71% over initial rewards, with sim-to-real transfer achieving 91% real-world success rate and 94% sim-to-real accuracy.
HiReLC: Hierarchical Reinforcement Learning Framework for Joint Neural Network Pruning and Quantization
Researchers introduce HiReLC, a hierarchical ensemble-RL framework that automates joint quantization and structured pruning of deep neural networks. The system uses two-level agents — low-level agents selecting per-kernel compression configurations and high-level agents coordinating global budget allocation via Fisher Information-based sensitivity estimates. Experiments on Vision Transformers and CNNs achieve 5.99–6.72× parameter-storage compression with accuracy drops of 0.55–5.62% in most settings. The controller is architecture-agnostic, using a surrogate MLP and active learning loop to reduce policy evaluation cost.
CNeVA: Controllable neural variational agents for steerable traffic simulation
Researchers introduce Controllable Neural Variational Agents (CNeVA), a framework for traffic simulation that infers per-agent Gaussian behavior latents from discounted returns via conjugate variational updates, conditioning a rectified-flow trajectory generator with classifier-free guidance. The system enables interpretable steering along axes such as speed, acceleration, and safety compliance without sacrificing realism. Evaluated on the Waymo Open Motion Dataset, CNeVA achieves competitive realism while offering per-channel controllability absent from higher-ranked imitation baselines. The work also introduces soft eligibility gates to address reward signal scarcity near decision thresholds.
Neuronal Stochastic Attention Circuit (NSAC) for Probabilistic Representation Learning
Researchers introduce NSAC, a biologically-inspired continuous-time attention architecture that models attention logits as solutions to an Ornstein-Uhlenbeck stochastic differential equation, drawing on C. elegans Neuronal Circuit Policy wiring to induce Gaussian distributions over attention weights. The architecture enables joint quantification of aleatoric and epistemic uncertainty via a two-term objective combining Gaussian negative log-likelihood with an epistemic-separation regularizer. Empirical evaluation spans irregular time-series function approximation, multivariate regression, long-range forecasting, Industry 4.0 tasks, and autonomous vehicle lane-keeping, showing competitive accuracy with well-calibrated uncertainty estimates.
Program synthesis used to reverse-engineer transformer attention heads with executable Python surrogates
Researchers propose a pipeline that approximates transformer attention heads with executable Python programs generated by a language model, then re-ranked by held-out predictive accuracy. Applied to GPT-2, TinyLlama-1.1B, and Llama-3B, fewer than 1,000 programs reproduce attention patterns with >75% average IoU similarity on TinyStories. Replacing 25% of attention heads with programmatic surrogates incurs only a 16% average perplexity increase while preserving downstream QA performance, demonstrating a path toward symbolic transparency in neural models.