activity
20242026
collaborators

11 papers

cs.LG2026

How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL

Qifu Wen, Shuaijun Liu, Zihan Zhou +2

Accurate posterior prediction need not require accurate approximation of Bayesian updates. We prove that an unbounded gap between the update maps can coexist with vanishing predict…

cs.RO2026

CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs

Shuaijun Liu, Qifu Wen, Shuyang Hao +5

World Action Models (WAMs) augment robot policies with action-conditioned predicted futures, but a plausible future alone does not justify changing the action that a bimanual polic…

cs.RO2026

When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents

Shuaijun Liu, Feiyang You, Xingwei Chen +1

Embodied agents replan frequently to recover from execution drift, partial observability, and coordination hazards, but each LLM-based replanning call can consume an accumulated te…

cs.RO2026

The Gate, Not the Cache: Gate Provenance Bounds the Closed-Loop Reliability of Training-Free VLA Token Skipping

Qi Luo, Shuaijun Liu, Hao Zhao +5

Token skipping is a widely used training-free way to accelerate vision--language--action (VLA) models by bypassing computation for most visual tokens at each control step according…

cs.AI2026

EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation

Yi Liu, TingFeng Hui, Wei Zhang +4

Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments are expensive to build, bri…

cs.LG2026

Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection

Yihang Peng, Peng Jin, Jie Gong +4

Parameter-efficient fine-tuning (PEFT) has become a practical route for adapting large language models to downstream tasks, with LoRA-style methods being particularly attractive be…