MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
arXiv:2606.09677v2 Announce Type: replace-cross Abstract: While discriminative models for multi-channel speech separation excel in reference-based metrics, they often exhibit suboptimal…
Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design
arXiv:2606.10493v1 Announce Type: cross Abstract: Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in…
Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderation of LLM Outputs
arXiv:2606.10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering. Existing approaches typically…
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
arXiv:2606.09079v2 Announce Type: replace-cross Abstract: Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory…
Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques
arXiv:2606.11140v1 Announce Type: cross Abstract: Data assimilation (DA) in subsurface flow entails calibrating model parameters to match observed data, typically…
Learning-Guided Integration Contours Construction for Fast Large-Scale Generalized Eigensolvers
arXiv:2511.01927v2 Announce Type: replace-cross Abstract: Solving large-scale Generalized Eigenvalue Problems (GEPs) is a fundamental yet computationally prohibitive task in science…
V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions
arXiv:2512.11995v2 Announce Type: replace-cross Abstract: While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified…
Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelism
arXiv:2606.09377v2 Announce Type: replace-cross Abstract: Formal neural network verification — proving that a network satisfies safety properties for *all* inputs…
Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
arXiv:2604.15414v2 Announce Type: replace-cross Abstract: Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on emph{single-model…
Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning
arXiv:2605.23595v3 Announce Type: replace-cross Abstract: The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems,…