arXiv AI
Jul 21
Trace-Based On-Policy Distillation for Masked Diffusion Language Models
arXiv:2607. 16872v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv Machine Learning
Jul 21
Sobek: Streaming Equivariant Tensor Product Convolutions
arXiv:2607. 18074v1 Announce Type: new Abstract: Equivariant graph neural networks repeatedly apply edge-conditioned tensor-product convolutions over graph edges.
arXiv Machine Learning
Jul 21
Online-Score-Aided Federated Learning for Resource-Constrained Wireless Clients with Continual Data Arrival
arXiv:2408. 05886v5 Announce Type: replace Abstract: Heterogeneous system configurations of distributed clients connected to the central server (CS) via a time-varying wireless network pose significant challenges for popular distributed machine learning (ML) algorithms such as federated learning (FL).
arXiv AI
Jul 21
Design and Validation of a Lightweight 1D CNN for Affective Touch Classification in Soft Plush Companions
arXiv:2607. 16196v1 Announce Type: new Abstract: Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies, yet their deformability and multichannel tactile sensing complicate the robust interpretation of human affect.
arXiv Machine Learning
Jul 21
Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?
arXiv:2607. 17425v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly decodable signals.
arXiv AI
Jul 21
WHALE: A Scalable Unified Model for Recommendation with Wukong-HSTU Architecture
arXiv:2607. 17017v1 Announce Type: cross Abstract: As scalability becomes increasingly important in recommendation modeling, recent architectures have advanced the modeling of two broad sources of ranking signals along separate paths: non-sequence features, including user, item, context, and cross features; and sequence features from user behavior histories.
arXiv AI
Jul 21
Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models
arXiv:2603. 08173v2 Announce Type: replace-cross Abstract: Quantization has become essential for the efficient deployment of speech processing systems.
arXiv AI
Jul 21
From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?
arXiv:2604. 01608v4 Announce Type: replace Abstract: Multi-agent systems (MAS) tackle complex tasks by distributing expertise, though this often comes at the cost of heavy coordination overhead, context fragmentation, and brittle phase ordering.
arXiv AI
Jul 21
TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization
arXiv:2607. 16973v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems increasingly power enterprise LLM applications, yet the vector retrieval layer introduces two underexplored challenges: (1) trained codebook quantizers may expose corpus statistics during index construction, creating a leakage channel in multi-tenant deployments, and (2) post-hoc filtering for tenant isolation degrades recall on selective queries.
arXiv Machine Learning
Jul 21
SurvCF(t): Counterfactual Explanations for Survival Analysis in Predictive Maintenance Multivariate Time Series Data
arXiv:2607. 16969v1 Announce Type: new Abstract: Predictive maintenance relies on accurate Remaining Useful Life estimation, often formulated using survival analysis over multivariate time-series data.
arXiv AI
Jul 21
Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?
arXiv:2607. 17558v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) offers a promising approach for training large language models without relying on a separate teacher model.
arXiv Machine Learning
Jul 21
DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training
arXiv:2604. 26256v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time -- is bottlenecked by skewed generation: long-tailed trajectories indispensable for model performance block the entire training pipeline.
arXiv Machine Learning
Jul 21
AQKA: Active Quantum Kernel Acquisition Under a Shot Budget
arXiv:2605. 14672v2 Announce Type: replace Abstract: Estimating an $N \times N$ quantum kernel from circuit fidelities requires $\Theta(N^2 S)$ measurement shots, the dominant bottleneck for deployment on near-term hardware.
arXiv Machine Learning
Jul 21
FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications
arXiv:2607. 18171v1 Announce Type: new Abstract: Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose efficient deployment requires application-specific decisions about placement, streaming, and intra-model parallelism.
arXiv AI
Jul 21
Spatiotemporal Facial Action Unit Detection using Twin Cycle Autoencoders for Driver Monitoring
arXiv:2607. 16760v1 Announce Type: cross Abstract: Driver monitoring systems (DMS) increasingly rely on facial cues to infer drowsiness, distraction, and cognitive load in real time.
arXiv Machine Learning
Jul 21
PLayer-FL: A Principled Approach to Personalized Layer-wise Cross-Silo Federated Learning
arXiv:2502. 08829v2 Announce Type: replace Abstract: Federated learning (FL) with non-IID data often degrades client performance below local training baselines.
arXiv Machine Learning
Jul 21
Deep Adaptive Bayesian Screening
arXiv:2607. 16927v1 Announce Type: cross Abstract: We introduce Deep Adaptive Bayesian Screening (DABS), a method for performing adaptive factorial screening in high-dimensional discrete design spaces.
arXiv AI
Jul 21
CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning
arXiv:2607. 17568v1 Announce Type: cross Abstract: Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups.
arXiv AI
Jul 21
Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillation
arXiv:2607. 16303v1 Announce Type: cross Abstract: Medical Vision-Language Models (Med-VLMs) require reliable reasoning from fine-grained visual evidence, yet existing models can produce plausible clinical answers by relying on language priors or medical templates rather than truly attending to diagnosis-critical regions.
arXiv Machine Learning
Jul 21
Preserving Clusters in Error-Bounded Lossy Compression of Scientific Particle Data
arXiv:2604. 18801v2 Announce Type: replace Abstract: Scientific particle simulations in cosmology, molecular dynamics, and fluid dynamics produce large-scale datasets whose storage, movement, and analysis increasingly rely on lossy compression.