1

D^2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving

Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management

Causally Motivated Sycophancy Mitigation for Large Language Models

Durable Quantization Conditioned Misalignment Attack on Large Language Models

Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View

DeNC: Unleash Neural Codecs in Video Streaming with Diffusion Enhancement

Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning

Mjölnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion

Cross-modal Representation Flattening for Multi-modal Domain Generalization

Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing