2 citations · 3 across the 59 of their papers we have counts for
13 papers · 1 filter
Do Dynamic Routers Need Memory? HeRo: History-Aware Routing for Efficient LLM Inference
Hongjin Lin, Wentao Wan, Keze Wang
Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, however, treat each routing dec…
ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation
Zhuojie Yang, Wentao Wan, Keze Wang
Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effe…
AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
Zhixing Zhang, Jesen Zhang, Hao Liu +4
Foundation models for agriculture are increasingly trained on massive spatiotemporal data (e.g., multi-spectral remote sensing, soil grids, and field-level management logs) and ach…
Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems
Jusheng Zhang, Yijia Fan, Kaitong Cai +6
Vision-Language Models (VLMs) enable powerful multi-agent systems, but scaling them is economically unsustainable: coordinating heterogeneous agents under information asymmetry oft…
Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction
Qinglin Zeng, Jing Yang, Keze Wang
Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based app…
Large Language Models as Discounted Bayesian Filters
Jensen Zhang, Jing Yang, Keze Wang
Large Language Models (LLMs) demonstrate strong few-shot generalization through in-context learning, yet their reasoning in dynamic and stochastic environments remains opaque. Prio…