3 citations · 8 across the 15 of their papers we have counts for
8 papers · 1 filter
Planarian: Managing Agent State with Statepoints
Jinnan Guo, Hao Mark Chen, Kapil Vaswani +2
LLM agents solve complex tasks by iteratively changing files, invoking local tools, and interacting with remote services, which modifies state across their local environment and re…
COGNIT-Guard: Calibrated Standalone Direct-Decision Guardrails with Heterogeneous CPU-NPU Confidence Cascading under Explicit Latency and False-Positive Constraints
Hao Chen
When must a foundation-model safety gateway generate tokens, and when should it directly output a calibrated decision? We study calibrated standalone direct-decision foundation mod…
HM-ROUTER: Joint Model and Harness Routing for Agentic Systems
Hao Mark Chen, Royson Lee, Yasuyuki Okoshi +3
Agent performance depends on both the underlying model and the harness that manages its tool use and execution. Selecting a suitable pair requires accounting for their compatibilit…
AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative Decoding
Shuang Liang, Hao Mark Chen, Zhiwen Mo +4
Speculative decoding verifies a tree of draft tokens in one target-model forward pass. For a mixture-of-experts (MoE) target, however, parallel verification can activate the union…
AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving
Hao Mark Chen, Jinnan Guo, Wayne Luk +1
Large language model agents increasingly act through stateful tools, yet model generation and environment execution remain serialized at every step. As decoding accelerates, tool e…
Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning
Wenxi Gao, Guanxi Lu, Didi Zhu +5
Unified multimodal models (UMMs) with interleaved reasoning, which generate both textual and visual steps as part of intermediate reasoning traces, have demonstrated great potentia…
DeepStack: Facilitating Co-Design Exploration of 3D DRAM-Stacked Accelerators for Distributed LLM Inference
Zhiwen Mo, Guoyu Li, Hao Mark Chen +11
Advances in hybrid bonding and packaging have driven growing interest in 3D DRAM-stacked AI accelerators. As large language models (LLMs) scale to hundreds of billions or trillions…
Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs
Hao Mark Chen, Zhiwen Mo, Royson Lee +6
Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their int…