12 citations · 37 across the 28 of their papers we have counts for
14 papers · 1 filter
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training
Shrey Pandit, Xuan-Phi Nguyen, Yiran Zhao +1
Training a Mixture-of-Experts (MoE) model at long context or large batch size fails as soon as any one component's peak allocation exceeds device memory, so the target is every pea…
Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation
Xuan-Phi Nguyen, Zeyu Leo Liu, Yang Li +4
On-policy self-distillation aims to improve upon reinforcement learning from verifiable rewards (RLVR) by providing token-level scores derived from privileged information, such as…
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…
Mental World Modeling
Hao Fei, Yiran Zhao
World models enable a predictive substrate for planning and action, yet existing formulations merely answer a physical question: what/where it is, and how will it evolve. Human beh…
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…
Multilingual Fine-Tuning via Localized Gradient Conflict Resolution
Long P. Hoang, Yiran Zhao, Wei Lu +1
Cross-lingual versatility has become a defining capability of Large Language Models (LLMs). However, fine-tuning these models often induces negative interference, where gains in on…
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…
In-Context Reinforcement Learning for Tool Use in Large Language Models
Yaoqi Ye, Yiran Zhao, Keyu Duan +4
While large language models (LLMs) exhibit strong reasoning abilities, their performance on complex tasks is often constrained by the limitations of their internal knowledge. A com…
ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning
Yiran Zhao, Yaoqi Ye, Xiang Liu +2
With the rapid advancement of commercial multi-modal models, image editing has garnered significant attention due to its widespread applicability in daily life. Despite impressive…
UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark
Yanlin Li, Minghui Guo, Kaiwen Zhang +13
In real-world multimodal applications, systems usually need to comprehend arbitrarily combined and interleaved multimodal inputs from users, while also generating outputs in any in…
Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs
Yiran Zhao, Lu Zhou, Xiaogang Xu +3
As artificial intelligence (AI) is increasingly deployed across domains, ensuring fairness has become a core challenge. However, the field faces a "Tower of Babel'' dilemma: fairne…
LACONIC: Length-Aware Constrained Reinforcement Learning for LLM
Chang Liu, Yiran Zhao, Lawrence Liu +3
Reinforcement learning (RL) has enhanced the capabilities of large language models (LLMs) through reward-driven training. Nevertheless, this process can introduce excessively long…
Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog
Yiran Zhao, Shengyang Zhou, Zijian Wu +7
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources. To reduce resource c…
DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection
Zhenhua Xu, Yiran Zhao, Mengting Zhong +4
The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either re…