arXiv AI
Jun 9
End-to-End Context Compression at Scale
arXiv:2606. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv AI
Jun 9
I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
arXiv:2509. 10334v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost.
arXiv AI
Jun 9
TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks
arXiv:2510. 16028v4 Announce Type: replace-cross Abstract: Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces).
arXiv Machine Learning
Jun 9
Zero Touch Predictive Orchestration: Automating Time-Series Models for the Cloud-Edge Continuum
arXiv:2606. 09787v1 Announce Type: new Abstract: The Cloud-Edge Continuum (CEC) enables latency-critical applications by distributing resources to the far edge, but its extreme volatility makes proactive Zero Touch Management via time-series forecasting essential.
arXiv AI
Jun 9
DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs
arXiv:2601. 07994v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts.
arXiv AI
Jun 9
CANS: Accelerating Multiuser Collaborative Edge Inference via Cooperative Autodidactic NeuroSurgeon
arXiv:2606. 09175v1 Announce Type: cross Abstract: Recently, mobile edge computing (MEC)-enabled collaborative deep neural network (DNN) inference has emerged as a promising approach for delivering intelligent services to resource-constrained mobile devices.
arXiv AI
Jun 9
Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation
arXiv:2605. 03058v2 Announce Type: replace-cross Abstract: A central goal of explainable AI is to express large language model (LLM) decision logic symbolically and ground it in internal mechanisms.
arXiv AI
Jun 9
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
arXiv:2605. 11855v2 Announce Type: replace-cross Abstract: Sequence learning is dominated by Transformers and parallelizable recurrent neural networks (RNNs) such as state-space models, yet learning long-term dependencies remains challenging, and state-of-the-art designs trade power consumption for performance.
arXiv Machine Learning
Jun 9
Efficient Traffic Prediction at Scale: A Systematic Study of STGCN Architectural Depth
arXiv:2606. 09539v1 Announce Type: new Abstract: Spatio-temporal graph neural networks (STGNNs) have become the dominant approach for traffic prediction, yet their computational requirements pose challenges for practical deployment in intelligent transportation systems (ITS).
arXiv AI
Jun 9
Post-Trained MoE Can Skip Half Experts via Self-Distillation
arXiv:2605. 18643v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts in an input-dependent manner.
arXiv AI
Jun 9
APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing
arXiv:2606. 08761v1 Announce Type: cross Abstract: W4A4 quantization promises full utilization of INT4 Tensor Cores, yet group dequantization overhead on CUDA Cores has driven existing systems to mixed-precision fallbacks.
arXiv Machine Learning
Jun 9
A Unified Structured Query Understanding Framework for Industrial Semantic Search
arXiv:2605. 27441v2 Announce Type: replace-cross Abstract: Query understanding in large-scale industrial search systems is typically implemented as a cascade of disparate, task-specific components.
arXiv AI
Jun 9
Q-Delta: Beyond Key-Value Associative State Evolution
arXiv:2606. 08804v1 Announce Type: new Abstract: Linear attention reformulates sequence modeling as recurrent state evolution, enabling efficient linear-time inference.
arXiv AI
Jun 9
Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin
arXiv:2606. 09012v1 Announce Type: cross Abstract: Post-training quantization (PTQ) converts a trained full-precision model into low-bit weights without task-level retraining, while quantization-aware training (QAT) incorporates quantization into the training loop.
arXiv AI
Jun 9
How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions
arXiv:2606. 08051v1 Announce Type: new Abstract: Financial transaction processing requires extracting structured merchant information from noisy, abbreviated bank transaction strings at scale.
arXiv AI
Jun 9
Trajectory-Refined Distillation
arXiv:2606. 08432v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollouts.
arXiv AI
Jun 9
From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs
arXiv:2606. 09508v1 Announce Type: new Abstract: Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts.
arXiv AI
Jun 9
FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting
arXiv:2606. 08896v1 Announce Type: new Abstract: Large-scale retail and industrial forecasting systems contain many heterogeneous time series whose lifecycle, sparsity, volatility, seasonality, spectral patterns, and contextual sensitivity differ substantially.
arXiv AI
Jun 9
A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics
arXiv:2601. 11541v2 Announce Type: replace-cross Abstract: To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Models (LLMs), this study evaluates a locally hosted Small Language Model (SLM).
arXiv AI
Jun 9
BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension
arXiv:2606. 08674v1 Announce Type: cross Abstract: Existing video generation frameworks treat sequence duration as an externally prescribed parameter -- fixed frame counts or text prompts -- producing clips whose temporal boundaries are decoupled from the statistical structure of real behavioral data.