16 papers
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference
Ben Wan, Yan Feng, Zihan Tang +4
DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural inf…
IFDNS: An Iterative Feedback-Driven Neuro-Symbolic Method for Faithful Logical Reasoning
Xiaoheng Wang, Tongxuan Liu, Zi Gong +5
Large language models (LLMs) have demonstrated impressive capabilities across a wide range of reasoning tasks, including logical and mathematical problem-solving. While prompt-base…
AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems
Yun Piao, Hongbo Min, Hang Su +28
The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remai…
From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation
Qingchuan Li, Mingyue Cheng, Zirui Liu +3
Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, underpinning scientific discovery, mathematical the…
ProServe: Unified Multi-Priority Request Scheduling for LLM Serving
Weizhe Huang, Tao Peng, Tongxuan Liu +4
The widespread deployment of large language models (LLMs) for interactive applications necessitates serving systems that can handle thousands of concurrent requests with diverse Se…
OOCO: Latency-disaggregated Architecture for Online-Offline Co-locate LLM Serving
Siyu Wu, Zihan Tang, Yuting Zeng +5
Large Language Models (LLMs) are increasingly deployed in both latency-sensitive online services and cost-sensitive offline workloads. Co-locating these workloads on shared serving…