collaborators

13 papers

cs.CL2026

Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning

Jinhu Qi, Minda Hu, Wentao Zhang +4

Large language models (LLMs) increasingly handle in-context learning (ICL) tasks where a long, novel context defines the rules, knowledge, and output schema for a series of questio…

cs.CL2026

TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning

Jinhu Qi, Wentao Zhang, Siu Man Ng +4

Travel planning is a demanding stress test for tool-using LLM agents: a usable itinerary is a single artifact that must be right along many axes at once - every flight, hotel, and…

cs.CV2026

Geometric Collapse: When Vision Models Fail to Verify Physical Causality

Wentao Zhang, Jinhu Qi, Weiqiang Jin +3

Recent progress in large-scale self-supervised learning has improved dense geometric prediction, but it remains unclear whether such scaling yields inference-time physical plausibi…

cs.LG2026

When Should the Teacher Move? Temporal Coupling and Stability in Self On-Policy Distillation

Haowei Guo, Baolong Bi, Ruicheng Zhang +2

Self on-policy distillation trains a student policy against a teacher derived from its own parameter history, yet the teacher's update schedule -- which governs the \emph{temporal…

cs.DS2026

One-Shot Klein Cutting Planes for Lipschitz Geodesically Convex Optimization in Hyperbolic Space

Yutong Zhang, Yaoran Yang, Yifan Zhu +1

Motivated by the COLT 2023 open problem of Criscitiello, Martínez-Rubio, and Boumal on deterministic first-order methods for Lipschitz geodesically convex optimization on Hadamard…

cs.AI2026

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning

Chusen Li, Zhou Liu, Shuigeng Zhou +1

Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain difficult to combine. Directl…