arXiv:2603.08026v1 Announce Type: cross Abstract: Masked Diffusion Language Models (MDLMs) enable parallel token decoding, providing a promising alternative to the sequential nature of autoregressive generation. However, their iterative denoising process remains computationally expensive because it repeatedly processes the entire sequence at every step. We observe that across these diffusion steps, most token representations remain stable; only a small subset, which we term salient tokens, contributes meaningfully to the next update. Leveraging this temporal sparsity, we present DyLLM, a training-free inference framework that accelerates decoding by selectively computing only these salient tokens. DyLLM identifies saliency by measuring the cosine similarity of attention contexts between adjacent denoising steps. It recomputes feed-forward and attention operations only for salient tokens while reusing cached activations for the remainder. Across diverse reasoning and code-generation benchmarks, DyLLM achieves up to 9.6x higher throughput while largely preserving the baseline accuracy of state-of-the-art models like LLaDA and Dream.

arXiv:2603.03932v1 Announce Type: cross Abstract: Offline Reinforcement Learning (RL) is a promising approach for next-generation wireless networks, where online exploration is unsafe and large amounts of operational data can be reused across the model lifecycle. However, the behavior of offline RL algorithms under genuinely stochastic dynamics -- inherent to wireless systems due to fading, noise, and traffic mobility -- remains insufficiently understood. We address this gap by evaluating Bellman-based (Conservative Q-Learning), sequence-based (Decision Transformers), and hybrid (Critic-Guided Decision Transformers) offline RL methods in an open-access stochastic telecom environment (mobile-env). Our results show that Conservative Q-Learning consistently produces more robust policies across different sources of stochasticity, making it a reliable default choice in lifecycle-driven AI management frameworks. Sequence-based methods remain competitive and can outperform Bellman-based approaches when sufficient high-return trajectories are available. These findings provide practical guidance for offline RL algorithm selection in AI-driven network control pipelines, such as O-RAN and future 6G functions, where robustness and data availability are key operational constraints.

arXiv:2603.02271v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are an emerging class of workloads critical for robotics and embodied AI at the edge. As these models scale, they demonstrate significant capability gains, yet they must be deployed locally to meet the strict latency requirements of real-time applications. This paper characterizes VLA performance on two generations of edge hardware, viz. the Nvidia Jetson Orin and Thor platforms. Using MolmoAct-7B, a state-of-the-art VLA model, we identify a primary execution bottleneck: up to 75% of end-to-end latency is consumed by the memory-bound action-generation phase. Through analytical modeling and simulations, we project the hardware requirements for scaling to 100B parameter models. We also explore the impact of high-bandwidth memory technologies and processing-in-memory (PIM) as promising future pathways in edge systems for embodied AI.

arXiv:2602.05695v2 Announce Type: replace Abstract: Large Language Models (LLMs) inference is central to modern AI applications, dominating worldwide datacenter workloads, making it critical to predict its energy footprint. Existing approaches estimate energy consumption as a simple linear function of input and output sequence. However, by analyzing the autoregressive structure of Transformers, which implies a fundamentally non-linear relationship between input and output sequence lengths and energy consumption, we demonstrate the existence of a generation energy minima. Peak efficiency occurs with short-to-moderate inputs and medium-length outputs, while efficiency drops sharply for long inputs or very short outputs. Consequently, we propose SweetSpot, an analytical model derived from the computational and memory-access complexity of the Transformer architecture, which accurately characterizes the efficiency curve as a function of input and output lengths. To assess accuracy, we measure energy consumption using TensorRT-LLM on NVIDIA H100 GPUs across a diverse set of LLMs ranging from 1B to 9B parameters, including OPT, LLaMA, Gemma, Falcon, Qwen2, and Granite. We test input and output lengths from 64 to 4096 tokens and achieve a mean MAPE of 1.79%. Our results show that aligning sequence lengths with these efficiency "sweet spots" reduce energy usage, up to 33.41x, enabling informed truncation, summarization, and adaptive generation strategies in production systems.

arXiv:2602.14236v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) face a critical memory bottleneck when processing long-form video content due to the linear growth of the Key-Value (KV) cache with sequence length. Existing solutions predominantly employ reactive eviction strategies that compute full attention matrices before discarding tokens, resulting in substantial computational waste. We propose Sali-Cache, a novel a priori optimization framework that implements dual-signal adaptive caching through proactive memory management. By integrating a temporal filter based on optical flow analysis for detecting inter-frame redundancy and a spatial filter leveraging saliency detection for identifying visually significant regions, Sali-Cache intelligently manages memory allocation before entering computationally expensive attention operations. Experimental evaluation on the LLaVA 1.6 architecture demonstrates that our method achieves a 2.20x compression ratio in effective memory usage while maintaining 100% accuracy across BLEU, ROUGE-L, and Exact Match metrics. Furthermore, under identical memory budget constraints, Sali-Cache preserves context-rich features over extended temporal durations without degrading model performance, enabling efficient processing of long-form video content on consumer-grade hardware.