works on

From the 1 of 21 linked papers with an AI index.

collaborators

21 papers

cs.AI2026

Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation

Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3

Outcome verifiers score completed reasoning traces but do not assign credit to intermediate tokens. Privileged self-distillation attempts to fill this gap by rescoring a model's ow…

cs.AI2026

TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models

Yidong Wang, Yan Zhan, Ziteng Feng +16

Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond handcrafted rewards or task-spe…

cs.CL2026

Mental World Modeling

Hao Fei, Yiran Zhao

The paper introduces Mental World Modeling (MWM), a framework that integrates agents' mental states (beliefs, desires, intentions) into world models, and presents a training‑free b…

cs.DC2026

Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models

Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3

This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models. It is a training paradigm that combines and specializes various existing and novel paral…

cs.AI2026

Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

Long P. Hoang, Yiran Zhao, Wei Lu +1

The rapid evolution of Large Language Models (LLMs) has established cross-lingual versatility as a defining feature of modern systems. However, fine-tuning these models frequently…

cs.CR2026

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

Chiyu Zhang, Huiqin Yang, Bendong Jiang +8

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, whe…