11 papers
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…
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…
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…
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…
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…
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…