10 papers
LiveServe: Interaction-Aware Serving for Real-Time Omni-Modal LLMs
Xiangyu Zhi, Peiqi Yin, Sheng Guan +3
Realtime omni-modal LMs support speech-centric conversations where users stream inputs, hear generated audio, and interrupt freely. Existing Omni-LM serving systems still rely on t…
RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents
Zijie Dai, Shiyuan Deng, Sheng Guan +4
Memory systems often organize user-agent interactions as retrievable external memory and are crucial for long-running agents by overcoming the limited context windows of LLMs. Howe…
SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management
Shengyue Guan, Yihao Liu, Lang Cao
Large language models (LLMs) have shown promise in complex reasoning and tool-based decision making, motivating their application to real-world supply chain management. However, su…
Scalable Prompt Routing via Fine-Grained Latent Task Discovery
Yunyi Zhang, Soji Adeshina, Sheng Guan +5
Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools s…
VisualDeltas: Learning Preferences from Visual Quality Perturbations
Hailiang Huang, Yihao Liu, Shengyue Guan +2
We present VisualDeltas, a lightweight preference-learning framework that extracts supervision from visual quality variations in multimodal data. By leveraging the systematic impac…
Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning
Zhi Zhang, Zhen Han, Costas Mavromatis +9
Reinforcement learning (RL) plays a central role in large language model (LLM) post-training. Among existing approaches, Group Relative Policy Optimization (GRPO) is widely used, e…