3

Beyond Left-to-Right: A Survey of Decoding Schedulers in Diffusion Language Models
Autoregressive language models decode one token at a time, a sequential bottleneck that caps throughput and compounds errors as …
PDF Cite DOI
Beyond Left-to-Right: A Survey of Decoding Schedulers in Diffusion Language Models
RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolution
Ride-sharing, which allows multiple passengers with different origin-destination (OD) pairs to share a single vehicle, is a challenging …
PDF Cite Code DOI
RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolution
Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning
Many reinforcement learning systems, from fleet management to traffic signal control, must serve an objective that changes dynamically …
PDF Cite Code DOI
Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning
Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads
A multiplicative dual-encoder network computes a real-valued output for a pair of inputs as the inner product of their separate …
PDF Cite Code DOI
Aggregate in the Advantage, Not the Ratio: A Canonical-Form Analysis of Cooperative Multi-Agent Policy Optimization
Multi-agent policy optimization, exemplified by PPO-based methods, is a key branch of cooperative Multi-Agent Reinforcement Learning …
PDF Cite Code DOI
Aggregate in the Advantage, Not the Ratio: A Canonical-Form Analysis of Cooperative Multi-Agent Policy Optimization
Optimizing Denoising Trajectories in dLLMs: A Lightweight Evolutionary Heuristic Approach
Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to conventional Auto-Regressive (AR) Large …
PDF Cite Code DOI
Optimizing Denoising Trajectories in dLLMs: A Lightweight Evolutionary Heuristic Approach
RideGym: A Standardized Interface for Real-World Large-Scale Ride-Sharing System
Ride-sharing has become an essential component of modern urban transportation and has attracted significant attention across computer …
PDF Cite Code Project DOI
RideGym: A Standardized Interface for Real-World Large-Scale Ride-Sharing System
Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus
Cooperative multi-agent reinforcement learning (MARL) is widely used to address large joint observation and action spaces by …
PDF Cite Code DOI
Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus
AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt
Accurate traffic prediction is essential for Intelligent Transportation Systems, including ride-hailing, urban road planning, and …
PDF Cite Code DOI
AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt