1 citations · 1 across the 9 of their papers we have counts for
14 papers
ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery
Houcheng Jiang, Mao Zheng, Mingyang Song +4
Structured pruning reduces the deployment cost of reasoning language models, but the resulting capability degradation can hinder subsequent on-policy distillation (OPD) recovery. B…
Learning Robust Personalized Prompts for LLM-Driven Sequential Recommendation
Xiaolin Zheng, Qiyong Zhong, Jiajie Su +1
LLM-driven sequential recommendation formulates next-item prediction as autoregressive generation conditioned on natural-language prompts. However, minor wording changes in semanti…
MAS-OPD: On-Policy Distillation for Multi-agent Systems
Qiyong Zhong, Mao Zheng, Mingyang Song +5
Multi-agent systems (MAS) split a task across specialized roles and are promising on complex tasks, yet a prevailing approach relies on inference-time orchestration alone. General-…
USA: Update-aware SAM for Cross-domain On-Policy Disitllation of Language Agents
Qiyong Zhong, Mao Zheng, Mingyang Song +6
On-policy distillation instils multi-turn agentic reasoning through dense token-level supervision on the student's own trajectories, but a single domain saturates early, so further…
Data-Free On-Policy Distillation: How Far Can We Go Without External Data?
Gengsheng Li, Mao Zheng, Mingyang Song +10
On-policy distillation (OPD) is increasingly applied to frontier foundation model post-training. Prior work in this area has largely focused on algorithmic advances, yet it remains…
RePolicy: Learning to Select and Apply Safety Policies for Agent Safeguards
Houcheng Jiang, Boxuan Zhang, Qiyong Zhong +3
Agent safeguards must determine whether an agent's behavior violates the safety rules of the current task, environment, and user. Because these rules vary across contexts, a safegu…
EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models
Jie Sun, Mao Zheng, Mingyang Song +7
Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillat…
On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
Gengsheng Li, Mao Zheng, Mingyang Song +8
Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large…
SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
Jie Sun, Mao Zheng, Mingyang Song +6
On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparabl…
SOD: Step-wise On-policy Distillation for Small Language Model Agents
Qiyong Zhong, Mao Zheng, Mingyang Song +5
Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model capacity. While reinforcement…
An item is worth one token in Multimodal Large Language Models-based Sequential Recommendation
Qiyong Zhong, Jiajie Su, Ming Yang +3
Sequential recommendations (SR) predict users' future interactions based on their historical behavior. The rise of Large Language Models (LLMs) has brought powerful generative and…
Pctx: Tokenizing Personalized Context for Generative Recommendation
Qiyong Zhong, Jiajie Su, Yunshan Ma +2
Generative recommendation (GR) models tokenize each action into a few discrete tokens (called semantic IDs) and autoregressively generate the next tokens as predictions, showing ad…
Distilling Transitional Pattern to Large Language Models for Multimodal Session-based Recommendation
Jiajie Su, Qiyong Zhong, Yunshan Ma +5
Session-based recommendation (SBR) predicts the next item based on anonymous sessions. Traditional SBR explores user intents based on ID collaborations or auxiliary content. To fur…
LoGoFair: Post-Processing for Local and Global Fairness in Federated Learning
Li Zhang, Chaochao Chen, Zhongxuan Han +2
Federated learning (FL) has garnered considerable interest for its capability to learn from decentralized data sources. Given the increasing application of FL in decision-making sc…