collaborators

46 papers

cs.AI2026

KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn

Yoonjoo Lee, Hyoungwook Jin, Tae Soo Kim +3

To effectively collaborate with users on knowledge-intensive tasks, Large Language Models (LLMs) must perform information calibration: matching content to a user's evolving underst…

cs.CL2026

Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability

Sizhe Zhou, Sheldon Yu, Hui Wei +8

The paper systematically investigates how large language model agents can use a filesystem of markdown files as long‑term memory, examining different organization strategies, tools…

cs.AI2026

How Hard Does It Think? Analyzing Step-Aware Reasoning Energy in LLM Chain-of-Thought Trajectories

Hui Wei, Junda Wu, Sheldon Yu +8

Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpretability methods rely on ou…

cs.LG2026

RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts

Yuxin Xiong, Xunyi Jiang, Rohan Surana +8

Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group u…

cs.AI2026

Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

Sheldon Yu, Tong Yu, Xunyi Jiang +6

Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable. Existing methods for shap…

cs.SD2026

AutoSIFT: Automatic Style Sifting for Controllable Speech Generation with Arbitrary Style Infilling

Haowei Lou, Junda Wu, Chengkai Huang +4

AutoSIFT is a text-to-speech framework that separates speaking style into explicit categories (e.g., emotion, age) and residual prosodic details, allowing users to edit specific st…